moved posed scene to SharedAssets

5 年前 · 27ded81d
--- a/Project/Assets/ML-Agents/Examples/SharedAssets/Scenes.meta
+++ b/Project/Assets/ML-Agents/Examples/SharedAssets/Scenes.meta
+fileFormatVersion: 2
+guid: 60bd92f6edd434a8c8a5089a08ca414b
+folderAsset: yes
+DefaultImporter:
+  externalObjects: {}
+  userData: 
+  assetBundleName: 
+  assetBundleVariant: 
--- a/results/CrawlerDynamic/CrawlerDynamic.nn
+++ b/results/CrawlerDynamic/CrawlerDynamic.nn
--- a/results/CrawlerDynamic/CrawlerDynamic/checkpoint
+++ b/results/CrawlerDynamic/CrawlerDynamic/checkpoint
+model_checkpoint_path: "model-1429.ckpt"
+all_model_checkpoint_paths: "model-1429.ckpt"
--- a/results/CrawlerDynamic/CrawlerDynamic/events.out.tfevents.1593650175.BrandonHunterHenry.local
+++ b/results/CrawlerDynamic/CrawlerDynamic/events.out.tfevents.1593650175.BrandonHunterHenry.local
+�K"	��J��A
brain.Event:2__p}]��	���J��A*�
+�
+HyperparametersB�
Btrainer_typeBppoBhyperparametersB�{'batch_size': 2024, 'buffer_size': 20240, 'learning_rate': 0.0003, 'beta': 0.005, 'epsilon': 0.2, 'lambd': 0.95, 'num_epoch': 3, 'learning_rate_schedule': 'linear'}Bnetwork_settingsBf{'normalize': True, 'hidden_units': 512, 'num_layers': 3, 'vis_encode_type': 'simple', 'memory': None}Breward_signalsB0{'extrinsic': {'gamma': 0.995, 'strength': 1.0}}B	init_pathBNoneBkeep_checkpointsB5Bcheckpoint_intervalB500000B	max_stepsB10000000Btime_horizonB1000Bsummary_freqB30000BthreadedBTrueB	self_playBNoneBbehavioral_cloningBNoneJ
+
+textԹN�
--- a/results/CrawlerDynamic/CrawlerDynamic/frozen_graph_def.pb
+++ b/results/CrawlerDynamic/CrawlerDynamic/frozen_graph_def.pb
--- a/results/CrawlerDynamic/CrawlerDynamic/model-1429.ckpt.index
+++ b/results/CrawlerDynamic/CrawlerDynamic/model-1429.ckpt.index
+action_output_shape(5��8
global_step (5��W�
is_continuous_control (5�e
memory_size (5�{:
normalization_steps (5��W�optimizer//extrinsic_value/bias (5�{:kernel	� (�5/�=main_graph_0/hidden_0/bias� �(�5�3"�!kernel
+�� � (��5���1/bias� ��(�5�3"�!kernel
+�� ��(��@5��Ҍ2/bias� ��Q(�5�3"�!kernel
+�� ��Q(��@5�71�$optimizer//extrinsic_value/bias/Adam ���(5�{:/_1 ���(5�{:1optimizer//optimizer//extrinsic_value/kernel/Adam	� ���(�5�3"�1_1	� ���(�5�3"�main_graph_0/hidden_0/bias/Adam� ���(�5�3"�5_1� ���(�5�3"�,kernel/Adam
+�� ���(��5��>7_1
+�� ���(��5��>*1/bias/Adam� ���(�5�3"�5_1� ���(�5�3"�,kernel/Adam
+�� ���(��@5+��7_1
+�� ���(��@5+��*2/bias/Adam� ���(�5�3"�5_1� ���(�5�3"�,kernel/Adam
+�� ���(��@5+��7_1
+�� ���(��@5+��policy/log_std/Adam ���(P5C+�f_1 ���(P5C+�f1optimizer//policy/main_graph_0/hidden_0/bias/Adam� ���(�5�3"�1_1� ���(�5�3"�(kernel/Adam
+�� ���(��5��>3_1
+�� ���(��5��>&1/bias/Adam� ���(�5�3"�1_1� ���(�5�3"�(kernel/Adam
+�� ���(��@5+��3_1
+�� ���(��@5+��&2/bias/Adam� ���(�5�3"�1_1� ���(�5�3"�(kernel/Adam
+�� ���(��@5+��3_1
+�� ���(��@5+��u/bias/Adam ���(P5C+�f_1 ���(P5C+�fkernel/Adam	� ���(��5c?c _1	� ���(��5c?coptimizer/beta1_power ���(5����2_power ���(5����policy/log_std ���(P5C+�fmain_graph_0/hidden_0/bias� ���(�5�3"�kernel
+�� ���(��5]�=�1/bias� ���(�5�3"�kernel
+�� ���(��@5����2/bias� ���(�5�3"�kernel
+�� ���(��@5
+e�gu/bias ���(P5C+�f
+kernel	� ���(��5v�E�running_mean� ���(�5^���variance� ���(�5
+�1trainer_major_version ���(5�{:	inor_version ���(5�'yU
patch_version ���(5�{:version_number ���(5��s'��	�H�{����w��2%���W���$uG�
--- a/results/CrawlerDynamic/CrawlerDynamic/model-1429.ckpt.meta
+++ b/results/CrawlerDynamic/CrawlerDynamic/model-1429.ckpt.meta
--- a/results/CrawlerDynamic/CrawlerDynamic/raw_graph_def.pb
+++ b/results/CrawlerDynamic/CrawlerDynamic/raw_graph_def.pb
--- a/results/CrawlerDynamic/configuration.yaml
+++ b/results/CrawlerDynamic/configuration.yaml
+behaviors:
+  CrawlerDynamic:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 2024
+      buffer_size: 20240
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: linear
+    network_settings:
+      normalize: true
+      hidden_units: 512
+      num_layers: 3
+      vis_encode_type: simple
+      memory: null
+    reward_signals:
+      extrinsic:
+        gamma: 0.995
+        strength: 1.0
+    init_path: null
+    keep_checkpoints: 5
+    checkpoint_interval: 500000
+    max_steps: 10000000
+    time_horizon: 1000
+    summary_freq: 30000
+    threaded: true
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: null
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  seed: -1
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: false
+parameter_randomization: null
+curriculum: null
+checkpoint_settings:
+  run_id: CrawlerDynamic
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: true
+  train_model: false
+  inference: false
+debug: false
--- a/results/CrawlerDynamic/run_logs/timers.json
+++ b/results/CrawlerDynamic/run_logs/timers.json
+{
+    "name": "root",
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1593650162",
+        "python_version": "3.6.4 (default, Mar  1 2018, 18:36:42) \n[GCC 4.2.1 Compatible Apple LLVM 9.0.0 (clang-900.0.39.2)]",
+        "command_line_arguments": "/Users/brandonh/unity_projects/ml-agents-master/ml-agents/venv/bin/mlagents-learn config/ppo/CrawlerDynamic.yaml --run-id=CrawlerDynamic --force",
+        "mlagents_version": "0.18.0.dev0",
+        "mlagents_envs_version": "0.18.0.dev0",
+        "communication_protocol_version": "1.0.0",
+        "tensorflow_version": "2.2.0",
+        "end_time_seconds": "1593650180"
+    },
+    "total": 18.675483288941905,
+    "count": 1,
+    "self": 0.008750283974222839,
+    "children": {
+        "run_training.setup": {
+            "total": 0.015203848015516996,
+            "count": 1,
+            "self": 0.015203848015516996
+        },
+        "TrainerController.start_learning": {
+            "total": 18.651529156952165,
+            "count": 1,
+            "self": 1.732642306946218,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 13.572397847892717,
+                    "count": 1,
+                    "self": 13.572397847892717
+                },
+                "TrainerController.advance": {
+                    "total": 3.0705842591123655,
+                    "count": 235,
+                    "self": 0.002972850692458451,
+                    "children": {
+                        "env_step": {
+                            "total": 3.067611408419907,
+                            "count": 235,
+                            "self": 2.728578581358306,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 0.33576088724657893,
+                                    "count": 235,
+                                    "self": 0.007079660310409963,
+                                    "children": {
+                                        "NNPolicy.evaluate": {
+                                            "total": 0.32868122693616897,
+                                            "count": 166,
+                                            "self": 0.32868122693616897
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.0032719398150220513,
+                                    "count": 234,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 17.95689078711439,
+                                            "count": 234,
+                                            "is_parallel": true,
+                                            "self": 15.592823190963827,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.003518798970617354,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00029500690288841724,
+                                                            "children": {
+                                                                "_process_vector_observation": {
+                                                                    "total": 0.0032237920677289367,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0032237920677289367
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.0244212350808084,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0002589779905974865,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0002669510431587696,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0002669510431587696
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.023314381018280983,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.023314381018280983
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.000580925028771162,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00011981092393398285,
+                                                                    "children": {
+                                                                        "_process_vector_observation": {
+                                                                            "total": 0.0004611141048371792,
+                                                                            "count": 2,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0004611141048371792
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 2.364067596150562,
+                                                    "count": 233,
+                                                    "is_parallel": true,
+                                                    "self": 0.035590133047662675,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 0.03359149140305817,
+                                                            "count": 233,
+                                                            "is_parallel": true,
+                                                            "self": 0.03359149140305817
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 2.196396351675503,
+                                                            "count": 233,
+                                                            "is_parallel": true,
+                                                            "self": 2.196396351675503
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 0.09848962002433836,
+                                                            "count": 233,
+                                                            "is_parallel": true,
+                                                            "self": 0.022750661824829876,
+                                                            "children": {
+                                                                "_process_vector_observation": {
+                                                                    "total": 0.07573895819950849,
+                                                                    "count": 466,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.07573895819950849
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 3.962998744100332e-05,
+                    "count": 1,
+                    "self": 3.962998744100332e-05,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 3.0491049140691757,
+                                    "count": 12027,
+                                    "is_parallel": true,
+                                    "self": 0.19714495609514415,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 2.8519599579740316,
+                                            "count": 12027,
+                                            "is_parallel": true,
+                                            "self": 2.8519599579740316
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_model": {
+                    "total": 0.275865113013424,
+                    "count": 1,
+                    "self": 0.00018105306662619114,
+                    "children": {
+                        "Trainer.save_model": {
+                            "total": 0.2756840599467978,
+                            "count": 1,
+                            "self": 0.2756840599467978
+                        }
+                    }
+                }
+            }
+        }
+    }
+}
--- a/results/CrawlerDynamic/run_logs/training_status.json
+++ b/results/CrawlerDynamic/run_logs/training_status.json
+{
+    "metadata": {
+        "stats_format_version": "0.1.0",
+        "mlagents_version": "0.18.0.dev0",
+        "tensorflow_version": "2.2.0"
+    }
+}
--- a/results/CrawlerStatic/CrawlerStatic.nn
+++ b/results/CrawlerStatic/CrawlerStatic.nn
--- a/results/CrawlerStatic/CrawlerStatic/checkpoint
+++ b/results/CrawlerStatic/CrawlerStatic/checkpoint
+model_checkpoint_path: "model-1548.ckpt"
+all_model_checkpoint_paths: "model-1548.ckpt"
--- a/results/CrawlerStatic/CrawlerStatic/events.out.tfevents.1593650221.BrandonHunterHenry.local
+++ b/results/CrawlerStatic/CrawlerStatic/events.out.tfevents.1593650221.BrandonHunterHenry.local
+�K"	@K��A
brain.Event:2q�S�}]��	#2EK��A*�
+�
+HyperparametersB�
Btrainer_typeBppoBhyperparametersB�{'batch_size': 2024, 'buffer_size': 20240, 'learning_rate': 0.0003, 'beta': 0.005, 'epsilon': 0.2, 'lambd': 0.95, 'num_epoch': 3, 'learning_rate_schedule': 'linear'}Bnetwork_settingsBf{'normalize': True, 'hidden_units': 512, 'num_layers': 3, 'vis_encode_type': 'simple', 'memory': None}Breward_signalsB0{'extrinsic': {'gamma': 0.995, 'strength': 1.0}}B	init_pathBNoneBkeep_checkpointsB5Bcheckpoint_intervalB500000B	max_stepsB10000000Btime_horizonB1000Bsummary_freqB30000BthreadedBTrueB	self_playBNoneBbehavioral_cloningBNoneJ
+
+text�b�y
--- a/results/CrawlerStatic/CrawlerStatic/frozen_graph_def.pb
+++ b/results/CrawlerStatic/CrawlerStatic/frozen_graph_def.pb
--- a/results/CrawlerStatic/CrawlerStatic/model-1548.ckpt.index
+++ b/results/CrawlerStatic/CrawlerStatic/model-1548.ckpt.index
+action_output_shape(5��8
global_step (59
�
is_continuous_control (5�e
memory_size (5�{:
normalization_steps (59
�optimizer//extrinsic_value/bias (5�{:kernel	� (�5Q�[Umain_graph_0/hidden_0/bias� �(�5�3"�!kernel
+�� � (��5���-1/bias� ��(�5�3"�!kernel
+�� ��(��@5��D�2/bias� ��Q(�5�3"�!kernel
+�� ��Q(��@5�nm3$optimizer//extrinsic_value/bias/Adam ���(5�{:/_1 ���(5�{:1optimizer//optimizer//extrinsic_value/kernel/Adam	� ���(�5�3"�1_1	� ���(�5�3"�main_graph_0/hidden_0/bias/Adam� ���(�5�3"�5_1� ���(�5�3"�,kernel/Adam
+�� ���(��5��>7_1
+�� ���(��5��>*1/bias/Adam� ���(�5�3"�5_1� ���(�5�3"�,kernel/Adam
+�� ���(��@5+��7_1
+�� ���(��@5+��*2/bias/Adam� ���(�5�3"�5_1� ���(�5�3"�,kernel/Adam
+�� ���(��@5+��7_1
+�� ���(��@5+��policy/log_std/Adam ���(P5C+�f_1 ���(P5C+�f1optimizer//policy/main_graph_0/hidden_0/bias/Adam� ���(�5�3"�1_1� ���(�5�3"�(kernel/Adam
+�� ���(��5��>3_1
+�� ���(��5��>&1/bias/Adam� ���(�5�3"�1_1� ���(�5�3"�(kernel/Adam
+�� ���(��@5+��3_1
+�� ���(��@5+��&2/bias/Adam� ���(�5�3"�1_1� ���(�5�3"�(kernel/Adam
+�� ���(��@5+��3_1
+�� ���(��@5+��u/bias/Adam ���(P5C+�f_1 ���(P5C+�fkernel/Adam	� ���(��5c?c _1	� ���(��5c?coptimizer/beta1_power ���(5����2_power ���(5����policy/log_std ���(P5C+�fmain_graph_0/hidden_0/bias� ���(�5�3"�kernel
+�� ���(��5H�m�1/bias� ���(�5�3"�kernel
+�� ���(��@5~t&2/bias� ���(�5�3"�kernel
+�� ���(��@5��wLu/bias ���(P5C+�f
+kernel	� ���(��5�Hrunning_mean� ���(�5�i�variance� ���(�5{8�*trainer_major_version ���(5�{:	inor_version ���(5�'yU
patch_version ���(5�{:version_number ���(5��s'��	#�Ӹ����w��2%���W���$uG�
--- a/results/CrawlerStatic/CrawlerStatic/model-1548.ckpt.meta
+++ b/results/CrawlerStatic/CrawlerStatic/model-1548.ckpt.meta
--- a/results/CrawlerStatic/CrawlerStatic/raw_graph_def.pb
+++ b/results/CrawlerStatic/CrawlerStatic/raw_graph_def.pb
--- a/results/CrawlerStatic/configuration.yaml
+++ b/results/CrawlerStatic/configuration.yaml
+behaviors:
+  CrawlerStatic:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 2024
+      buffer_size: 20240
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: linear
+    network_settings:
+      normalize: true
+      hidden_units: 512
+      num_layers: 3
+      vis_encode_type: simple
+      memory: null
+    reward_signals:
+      extrinsic:
+        gamma: 0.995
+        strength: 1.0
+    init_path: null
+    keep_checkpoints: 5
+    checkpoint_interval: 500000
+    max_steps: 10000000
+    time_horizon: 1000
+    summary_freq: 30000
+    threaded: true
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: null
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  seed: -1
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: false
+parameter_randomization: null
+curriculum: null
+checkpoint_settings:
+  run_id: CrawlerStatic
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: true
+  train_model: false
+  inference: false
+debug: false
--- a/results/CrawlerStatic/run_logs/timers.json
+++ b/results/CrawlerStatic/run_logs/timers.json
+{
+    "name": "root",
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1593650208",
+        "python_version": "3.6.4 (default, Mar  1 2018, 18:36:42) \n[GCC 4.2.1 Compatible Apple LLVM 9.0.0 (clang-900.0.39.2)]",
+        "command_line_arguments": "/Users/brandonh/unity_projects/ml-agents-master/ml-agents/venv/bin/mlagents-learn config/ppo/CrawlerStatic.yaml --run-id=CrawlerStatic --force",
+        "mlagents_version": "0.18.0.dev0",
+        "mlagents_envs_version": "0.18.0.dev0",
+        "communication_protocol_version": "1.0.0",
+        "tensorflow_version": "2.2.0",
+        "end_time_seconds": "1593650226"
+    },
+    "total": 18.12544374493882,
+    "count": 1,
+    "self": 0.008958819904364645,
+    "children": {
+        "run_training.setup": {
+            "total": 0.010861473041586578,
+            "count": 1,
+            "self": 0.010861473041586578
+        },
+        "TrainerController.start_learning": {
+            "total": 18.10562345199287,
+            "count": 1,
+            "self": 1.6754347131354734,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 12.422339505981654,
+                    "count": 1,
+                    "self": 12.422339505981654
+                },
+                "TrainerController.advance": {
+                    "total": 3.6985495468834415,
+                    "count": 251,
+                    "self": 0.0033409703755751252,
+                    "children": {
+                        "env_step": {
+                            "total": 3.6952085765078664,
+                            "count": 251,
+                            "self": 3.3399255577242,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 0.35151520220097154,
+                                    "count": 251,
+                                    "self": 0.00889498379547149,
+                                    "children": {
+                                        "NNPolicy.evaluate": {
+                                            "total": 0.34262021840550005,
+                                            "count": 181,
+                                            "self": 0.34262021840550005
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.0037678165826946497,
+                                    "count": 250,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 17.38591544260271,
+                                            "count": 250,
+                                            "is_parallel": true,
+                                            "self": 14.477078061550856,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.00139414903242141,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0003408790798857808,
+                                                            "children": {
+                                                                "_process_vector_observation": {
+                                                                    "total": 0.0010532699525356293,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0010532699525356293
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.024324635043740273,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00019912992138415575,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00030468206387013197,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00030468206387013197
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.023232000996358693,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.023232000996358693
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0005888220621272922,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0001468671252951026,
+                                                                    "children": {
+                                                                        "_process_vector_observation": {
+                                                                            "total": 0.00044195493683218956,
+                                                                            "count": 2,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.00044195493683218956
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 2.9088373810518533,
+                                                    "count": 249,
+                                                    "is_parallel": true,
+                                                    "self": 0.0450834094081074,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 0.0420442724134773,
+                                                            "count": 249,
+                                                            "is_parallel": true,
+                                                            "self": 0.0420442724134773
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 2.6973308051237836,
+                                                            "count": 249,
+                                                            "is_parallel": true,
+                                                            "self": 2.6973308051237836
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 0.12437889410648495,
+                                                            "count": 249,
+                                                            "is_parallel": true,
+                                                            "self": 0.02756049670279026,
+                                                            "children": {
+                                                                "_process_vector_observation": {
+                                                                    "total": 0.09681839740369469,
+                                                                    "count": 498,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.09681839740369469
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 4.0604034438729286e-05,
+                    "count": 1,
+                    "self": 4.0604034438729286e-05,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 3.662667714059353,
+                                    "count": 12283,
+                                    "is_parallel": true,
+                                    "self": 0.25680465332698077,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 3.405863060732372,
+                                            "count": 12283,
+                                            "is_parallel": true,
+                                            "self": 3.405863060732372
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_model": {
+                    "total": 0.3092590819578618,
+                    "count": 1,
+                    "self": 0.00035183189902454615,
+                    "children": {
+                        "Trainer.save_model": {
+                            "total": 0.30890725005883723,
+                            "count": 1,
+                            "self": 0.30890725005883723
+                        }
+                    }
+                }
+            }
+        }
+    }
+}
--- a/results/CrawlerStatic/run_logs/training_status.json
+++ b/results/CrawlerStatic/run_logs/training_status.json
+{
+    "metadata": {
+        "stats_format_version": "0.1.0",
+        "mlagents_version": "0.18.0.dev0",
+        "tensorflow_version": "2.2.0"
+    }
+}
--- a/results/WalkerDy236/wdyclv-ppo/config/imitation/CrawlerStatic.yaml
+++ b/results/WalkerDy236/wdyclv-ppo/config/imitation/CrawlerStatic.yaml
+behaviors:
+  CrawlerStatic:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 2024
+      buffer_size: 20240
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: linear
+    network_settings:
+      normalize: true
+      hidden_units: 512
+      num_layers: 3
+      vis_encode_type: simple
+    reward_signals:
+      gail:
+        gamma: 0.99
+        strength: 1.0
+        encoding_size: 128
+        learning_rate: 0.0003
+        use_actions: false
+        use_vail: false
+        demo_path: Project/Assets/ML-Agents/Examples/Crawler/Demos/ExpertCrawlerSta.demo
+    keep_checkpoints: 5
+    max_steps: 10000000
+    time_horizon: 1000
+    summary_freq: 30000
+    threaded: true
+    behavioral_cloning:
+      demo_path: Project/Assets/ML-Agents/Examples/Crawler/Demos/ExpertCrawlerSta.demo
+      steps: 50000
+      strength: 0.5
+      samples_per_update: 0
--- a/results/WalkerDy236/wdyclv-ppo/config/imitation/FoodCollector.yaml
+++ b/results/WalkerDy236/wdyclv-ppo/config/imitation/FoodCollector.yaml
+behaviors:
+  FoodCollector:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 64
+      buffer_size: 10240
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: linear
+    network_settings:
+      normalize: false
+      hidden_units: 128
+      num_layers: 2
+      vis_encode_type: simple
+    reward_signals:
+      gail:
+        gamma: 0.99
+        strength: 0.1
+        encoding_size: 128
+        learning_rate: 0.0003
+        use_actions: false
+        use_vail: false
+        demo_path: Project/Assets/ML-Agents/Examples/FoodCollector/Demos/ExpertFood.demo
+    keep_checkpoints: 5
+    max_steps: 2000000
+    time_horizon: 64
+    summary_freq: 10000
+    threaded: true
+    behavioral_cloning:
+      demo_path: Project/Assets/ML-Agents/Examples/FoodCollector/Demos/ExpertFood.demo
+      steps: 0
+      strength: 1.0
+      samples_per_update: 0
--- a/results/WalkerDy236/wdyclv-ppo/config/imitation/Hallway.yaml
+++ b/results/WalkerDy236/wdyclv-ppo/config/imitation/Hallway.yaml
+behaviors:
+  Hallway:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 128
+      buffer_size: 1024
+      learning_rate: 0.0003
+      beta: 0.01
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: linear
+    network_settings:
+      normalize: false
+      hidden_units: 128
+      num_layers: 2
+      vis_encode_type: simple
+      memory:
+        sequence_length: 64
+        memory_size: 256
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+      gail:
+        gamma: 0.99
+        strength: 0.1
+        encoding_size: 128
+        learning_rate: 0.0003
+        use_actions: false
+        use_vail: false
+        demo_path: Project/Assets/ML-Agents/Examples/Hallway/Demos/ExpertHallway.demo
+    keep_checkpoints: 5
+    max_steps: 10000000
+    time_horizon: 64
+    summary_freq: 10000
+    threaded: true
--- a/results/WalkerDy236/wdyclv-ppo/config/imitation/PushBlock.yaml
+++ b/results/WalkerDy236/wdyclv-ppo/config/imitation/PushBlock.yaml
+behaviors:
+  PushBlock:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 128
+      buffer_size: 2048
+      learning_rate: 0.0003
+      beta: 0.01
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: linear
+    network_settings:
+      normalize: false
+      hidden_units: 256
+      num_layers: 2
+      vis_encode_type: simple
+    reward_signals:
+      gail:
+        gamma: 0.99
+        strength: 1.0
+        encoding_size: 128
+        learning_rate: 0.0003
+        use_actions: false
+        use_vail: false
+        demo_path: Project/Assets/ML-Agents/Examples/PushBlock/Demos/ExpertPush.demo
+    keep_checkpoints: 5
+    max_steps: 15000000
+    time_horizon: 64
+    summary_freq: 60000
+    threaded: true
--- a/results/WalkerDy236/wdyclv-ppo/config/imitation/Pyramids.yaml
+++ b/results/WalkerDy236/wdyclv-ppo/config/imitation/Pyramids.yaml
+behaviors:
+  Pyramids:
+    trainer_type: ppo
+    time_horizon: 128
+    max_steps: 1.0e7
+    hyperparameters:
+      batch_size: 128
+      beta: 0.01
+      buffer_size: 2048
+      epsilon: 0.2
+      lambd: 0.95
+      learning_rate: 0.0003
+      num_epoch: 3
+    network_settings:
+      num_layers: 2
+      normalize: false
+      hidden_units: 512
+    reward_signals:
+      extrinsic:
+        strength: 1.0
+        gamma: 0.99
+      curiosity:
+        strength: 0.02
+        gamma: 0.99
+        encoding_size: 256
+      gail:
+        strength: 0.01
+        gamma: 0.99
+        encoding_size: 128
+        demo_path: Project/Assets/ML-Agents/Examples/Pyramids/Demos/ExpertPyramid.demo
+    behavioral_cloning:
+      demo_path: Project/Assets/ML-Agents/Examples/Pyramids/Demos/ExpertPyramid.demo
+      strength: 0.5
+      steps: 150000
--- a/results/WalkerDy236/wdyclv-ppo/config/ppo/3DBall.yaml
+++ b/results/WalkerDy236/wdyclv-ppo/config/ppo/3DBall.yaml
+behaviors:
+  3DBall:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 64
+      buffer_size: 12000
+      learning_rate: 0.0003
+      beta: 0.001
+      epsilon: 0.2
+      lambd: 0.99
+      num_epoch: 3
+      learning_rate_schedule: linear
+    network_settings:
+      normalize: true
+      hidden_units: 128
+      num_layers: 2
+      vis_encode_type: simple
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+    keep_checkpoints: 5
+    max_steps: 500000
+    time_horizon: 1000
+    summary_freq: 12000
+    threaded: true
--- a/results/WalkerDy236/wdyclv-ppo/config/ppo/3DBallHard.yaml
+++ b/results/WalkerDy236/wdyclv-ppo/config/ppo/3DBallHard.yaml
+behaviors:
+  3DBallHard:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 1200
+      buffer_size: 12000
+      learning_rate: 0.0003
+      beta: 0.001
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: linear
+    network_settings:
+      normalize: true
+      hidden_units: 128
+      num_layers: 2
+      vis_encode_type: simple
+    reward_signals:
+      extrinsic:
+        gamma: 0.995
+        strength: 1.0
+    keep_checkpoints: 5
+    max_steps: 5000000
+    time_horizon: 1000
+    summary_freq: 12000
+    threaded: true
--- a/results/WalkerDy236/wdyclv-ppo/config/ppo/3DBall_randomize.yaml
+++ b/results/WalkerDy236/wdyclv-ppo/config/ppo/3DBall_randomize.yaml
+behaviors:
+  3DBall:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 64
+      buffer_size: 12000
+      learning_rate: 0.0003
+      beta: 0.001
+      epsilon: 0.2
+      lambd: 0.99
+      num_epoch: 3
+      learning_rate_schedule: linear
+    network_settings:
+      normalize: true
+      hidden_units: 128
+      num_layers: 2
+      vis_encode_type: simple
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+    keep_checkpoints: 5
+    max_steps: 500000
+    time_horizon: 1000
+    summary_freq: 12000
+    threaded: true
+
+parameter_randomization:
+  mass:
+    sampler_type: uniform
+    sampler_parameters:
+      min_value: 0.5
+      max_value: 10
+  scale:
+    sampler_type: uniform
+    sampler_parameters:
+      min_value: 0.75
+      max_value: 3
--- a/results/WalkerDy236/wdyclv-ppo/config/ppo/Basic.yaml
+++ b/results/WalkerDy236/wdyclv-ppo/config/ppo/Basic.yaml
+behaviors:
+  Basic:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 32
+      buffer_size: 256
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: linear
+    network_settings:
+      normalize: false
+      hidden_units: 20
+      num_layers: 1
+      vis_encode_type: simple
+    reward_signals:
+      extrinsic:
+        gamma: 0.9
+        strength: 1.0
+    keep_checkpoints: 5
+    max_steps: 500000
+    time_horizon: 3
+    summary_freq: 2000
+    threaded: true
--- a/results/WalkerDy236/wdyclv-ppo/config/ppo/Bouncer.yaml
+++ b/results/WalkerDy236/wdyclv-ppo/config/ppo/Bouncer.yaml
+behaviors:
+  Bouncer:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 1024
+      buffer_size: 10240
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: linear
+    network_settings:
+      normalize: true
+      hidden_units: 64
+      num_layers: 2
+      vis_encode_type: simple
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+    keep_checkpoints: 5
+    max_steps: 4000000
+    time_horizon: 64
+    summary_freq: 10000
+    threaded: true
--- a/results/WalkerDy236/wdyclv-ppo/config/ppo/CrawlerDynamic.yaml
+++ b/results/WalkerDy236/wdyclv-ppo/config/ppo/CrawlerDynamic.yaml
+behaviors:
+  CrawlerDynamic:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 2024
+      buffer_size: 20240
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: linear
+    network_settings:
+      normalize: true
+      hidden_units: 512
+      num_layers: 3
+      vis_encode_type: simple
+    reward_signals:
+      extrinsic:
+        gamma: 0.995
+        strength: 1.0
+    keep_checkpoints: 5
+    max_steps: 10000000
+    time_horizon: 1000
+    summary_freq: 30000
+    threaded: true
--- a/results/WalkerDy236/wdyclv-ppo/config/ppo/CrawlerStatic.yaml
+++ b/results/WalkerDy236/wdyclv-ppo/config/ppo/CrawlerStatic.yaml
+behaviors:
+  CrawlerStatic:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 2024
+      buffer_size: 20240
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: linear
+    network_settings:
+      normalize: true
+      hidden_units: 512
+      num_layers: 3
+      vis_encode_type: simple
+    reward_signals:
+      extrinsic:
+        gamma: 0.995
+        strength: 1.0
+    keep_checkpoints: 5
+    max_steps: 10000000
+    time_horizon: 1000
+    summary_freq: 30000
+    threaded: true
--- a/results/WalkerDy236/wdyclv-ppo/config/ppo/FoodCollector.yaml
+++ b/results/WalkerDy236/wdyclv-ppo/config/ppo/FoodCollector.yaml
+behaviors:
+  FoodCollector:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 1024
+      buffer_size: 10240
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: linear
+    network_settings:
+      normalize: false
+      hidden_units: 128
+      num_layers: 2
+      vis_encode_type: simple
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+    keep_checkpoints: 5
+    max_steps: 2000000
+    time_horizon: 64
+    summary_freq: 10000
+    threaded: true
--- a/results/WalkerDy236/wdyclv-ppo/config/ppo/GridWorld.yaml
+++ b/results/WalkerDy236/wdyclv-ppo/config/ppo/GridWorld.yaml
+behaviors:
+  GridWorld:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 32
+      buffer_size: 256
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: linear
+    network_settings:
+      normalize: false
+      hidden_units: 256
+      num_layers: 1
+      vis_encode_type: simple
+    reward_signals:
+      extrinsic:
+        gamma: 0.9
+        strength: 1.0
+    keep_checkpoints: 5
+    max_steps: 500000
+    time_horizon: 5
+    summary_freq: 20000
+    threaded: true
--- a/results/WalkerDy236/wdyclv-ppo/config/ppo/Hallway.yaml
+++ b/results/WalkerDy236/wdyclv-ppo/config/ppo/Hallway.yaml
+behaviors:
+  Hallway:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 128
+      buffer_size: 1024
+      learning_rate: 0.0003
+      beta: 0.01
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: linear
+    network_settings:
+      normalize: false
+      hidden_units: 128
+      num_layers: 2
+      vis_encode_type: simple
+      memory:
+        sequence_length: 64
+        memory_size: 128
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+    keep_checkpoints: 5
+    max_steps: 10000000
+    time_horizon: 64
+    summary_freq: 10000
+    threaded: true
--- a/results/WalkerDy236/wdyclv-ppo/config/ppo/PushBlock.yaml
+++ b/results/WalkerDy236/wdyclv-ppo/config/ppo/PushBlock.yaml
+behaviors:
+  PushBlock:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 128
+      buffer_size: 2048
+      learning_rate: 0.0003
+      beta: 0.01
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: linear
+    network_settings:
+      normalize: false
+      hidden_units: 256
+      num_layers: 2
+      vis_encode_type: simple
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+    keep_checkpoints: 5
+    max_steps: 2000000
+    time_horizon: 64
+    summary_freq: 60000
+    threaded: true
--- a/results/WalkerDy236/wdyclv-ppo/config/ppo/Pyramids.yaml
+++ b/results/WalkerDy236/wdyclv-ppo/config/ppo/Pyramids.yaml
+behaviors:
+  Pyramids:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 128
+      buffer_size: 2048
+      learning_rate: 0.0003
+      beta: 0.01
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: linear
+    network_settings:
+      normalize: false
+      hidden_units: 512
+      num_layers: 2
+      vis_encode_type: simple
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+      curiosity:
+        gamma: 0.99
+        strength: 0.02
+        encoding_size: 256
+        learning_rate: 0.0003
+    keep_checkpoints: 5
+    max_steps: 10000000
+    time_horizon: 128
+    summary_freq: 30000
+    threaded: true
--- a/results/WalkerDy236/wdyclv-ppo/config/ppo/Reacher.yaml
+++ b/results/WalkerDy236/wdyclv-ppo/config/ppo/Reacher.yaml
+behaviors:
+  Reacher:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 2024
+      buffer_size: 20240
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: linear
+    network_settings:
+      normalize: true
+      hidden_units: 128
+      num_layers: 2
+      vis_encode_type: simple
+    reward_signals:
+      extrinsic:
+        gamma: 0.995
+        strength: 1.0
+    keep_checkpoints: 5
+    max_steps: 20000000
+    time_horizon: 1000
+    summary_freq: 60000
+    threaded: true
--- a/results/WalkerDy236/wdyclv-ppo/config/ppo/SoccerTwos.yaml
+++ b/results/WalkerDy236/wdyclv-ppo/config/ppo/SoccerTwos.yaml
+behaviors:
+  SoccerTwos:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 2048
+      buffer_size: 20480
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: constant
+    network_settings:
+      normalize: false
+      hidden_units: 512
+      num_layers: 2
+      vis_encode_type: simple
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+    keep_checkpoints: 5
+    max_steps: 50000000
+    time_horizon: 1000
+    summary_freq: 10000
+    threaded: true
+    self_play:
+      save_steps: 50000
+      team_change: 200000
+      swap_steps: 2000
+      window: 10
+      play_against_latest_model_ratio: 0.5
+      initial_elo: 1200.0
--- a/results/WalkerDy236/wdyclv-ppo/config/ppo/StrikersVsGoalie.yaml
+++ b/results/WalkerDy236/wdyclv-ppo/config/ppo/StrikersVsGoalie.yaml
+behaviors:
+  Goalie:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 2048
+      buffer_size: 20480
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: constant
+    network_settings:
+      normalize: false
+      hidden_units: 512
+      num_layers: 2
+      vis_encode_type: simple
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+    keep_checkpoints: 5
+    max_steps: 50000000
+    time_horizon: 1000
+    summary_freq: 10000
+    threaded: true
+    self_play:
+      save_steps: 50000
+      team_change: 200000
+      swap_steps: 1000
+      window: 10
+      play_against_latest_model_ratio: 0.5
+      initial_elo: 1200.0
+  Striker:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 2048
+      buffer_size: 20480
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: constant
+    network_settings:
+      normalize: false
+      hidden_units: 512
+      num_layers: 2
+      vis_encode_type: simple
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+    keep_checkpoints: 5
+    max_steps: 50000000
+    time_horizon: 1000
+    summary_freq: 10000
+    threaded: true
+    self_play:
+      save_steps: 50000
+      team_change: 200000
+      swap_steps: 4000
+      window: 10
+      play_against_latest_model_ratio: 0.5
+      initial_elo: 1200.0
--- a/results/WalkerDy236/wdyclv-ppo/config/ppo/Tennis.yaml
+++ b/results/WalkerDy236/wdyclv-ppo/config/ppo/Tennis.yaml
+behaviors:
+  Tennis:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 2048
+      buffer_size: 20480
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: constant
+    network_settings:
+      normalize: true
+      hidden_units: 256
+      num_layers: 2
+      vis_encode_type: simple
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+    keep_checkpoints: 5
+    max_steps: 50000000
+    time_horizon: 1000
+    summary_freq: 10000
+    threaded: true
+    self_play:
+      save_steps: 50000
+      team_change: 100000
+      swap_steps: 2000
+      window: 10
+      play_against_latest_model_ratio: 0.5
+      initial_elo: 1200.0
--- a/results/WalkerDy236/wdyclv-ppo/config/ppo/VisualHallway.yaml
+++ b/results/WalkerDy236/wdyclv-ppo/config/ppo/VisualHallway.yaml
+behaviors:
+  VisualHallway:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 64
+      buffer_size: 1024
+      learning_rate: 0.0003
+      beta: 0.01
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: linear
+    network_settings:
+      normalize: false
+      hidden_units: 128
+      num_layers: 1
+      vis_encode_type: simple
+      memory:
+        sequence_length: 64
+        memory_size: 128
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+    keep_checkpoints: 5
+    max_steps: 10000000
+    time_horizon: 64
+    summary_freq: 10000
+    threaded: true
--- a/results/WalkerDy236/wdyclv-ppo/config/ppo/VisualPushBlock.yaml
+++ b/results/WalkerDy236/wdyclv-ppo/config/ppo/VisualPushBlock.yaml
+behaviors:
+  VisualPushBlock:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 64
+      buffer_size: 1024
+      learning_rate: 0.0003
+      beta: 0.01
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: linear
+    network_settings:
+      normalize: false
+      hidden_units: 128
+      num_layers: 1
+      vis_encode_type: simple
+      memory:
+        sequence_length: 32
+        memory_size: 128
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+    keep_checkpoints: 5
+    max_steps: 3000000
+    time_horizon: 64
+    summary_freq: 60000
+    threaded: true
--- a/results/WalkerDy236/wdyclv-ppo/config/ppo/VisualPyramids.yaml
+++ b/results/WalkerDy236/wdyclv-ppo/config/ppo/VisualPyramids.yaml
+behaviors:
+  VisualPyramids:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 64
+      buffer_size: 2024
+      learning_rate: 0.0003
+      beta: 0.01
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: linear
+    network_settings:
+      normalize: false
+      hidden_units: 256
+      num_layers: 1
+      vis_encode_type: simple
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+      curiosity:
+        gamma: 0.99
+        strength: 0.01
+        encoding_size: 256
+        learning_rate: 0.0003
+    keep_checkpoints: 5
+    max_steps: 10000000
+    time_horizon: 128
+    summary_freq: 10000
+    threaded: true
--- a/results/WalkerDy236/wdyclv-ppo/config/ppo/WalkerDynamic.yaml
+++ b/results/WalkerDy236/wdyclv-ppo/config/ppo/WalkerDynamic.yaml
+behaviors:
+  WalkerDynamic:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 2048
+      buffer_size: 20480
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: linear
+    network_settings:
+      normalize: true
+      hidden_units: 512
+      num_layers: 3
+      vis_encode_type: simple
+    reward_signals:
+      extrinsic:
+        gamma: 0.995
+        strength: 1.0
+    keep_checkpoints: 5
+    max_steps: 20000000
+    time_horizon: 1000
+    summary_freq: 30000
+    threaded: true
--- a/results/WalkerDy236/wdyclv-ppo/config/ppo/WalkerStatic.yaml
+++ b/results/WalkerDy236/wdyclv-ppo/config/ppo/WalkerStatic.yaml
+behaviors:
+  WalkerStatic:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 2048
+      buffer_size: 20480
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: linear
+    network_settings:
+      normalize: true
+      hidden_units: 512
+      num_layers: 3
+      vis_encode_type: simple
+    reward_signals:
+      extrinsic:
+        gamma: 0.995
+        strength: 1.0
+    keep_checkpoints: 5
+    max_steps: 20000000
+    time_horizon: 1000
+    summary_freq: 30000
+    threaded: true
--- a/results/WalkerDy236/wdyclv-ppo/config/ppo/WallJump.yaml
+++ b/results/WalkerDy236/wdyclv-ppo/config/ppo/WallJump.yaml
+behaviors:
+  BigWallJump:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 128
+      buffer_size: 2048
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: linear
+    network_settings:
+      normalize: false
+      hidden_units: 256
+      num_layers: 2
+      vis_encode_type: simple
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+    keep_checkpoints: 5
+    max_steps: 20000000
+    time_horizon: 128
+    summary_freq: 20000
+    threaded: true
+  SmallWallJump:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 128
+      buffer_size: 2048
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: linear
+    network_settings:
+      normalize: false
+      hidden_units: 256
+      num_layers: 2
+      vis_encode_type: simple
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+    keep_checkpoints: 5
+    max_steps: 5000000
+    time_horizon: 128
+    summary_freq: 20000
+    threaded: true
--- a/results/WalkerDy236/wdyclv-ppo/config/ppo/WallJump_curriculum.yaml
+++ b/results/WalkerDy236/wdyclv-ppo/config/ppo/WallJump_curriculum.yaml
+behaviors:
+  BigWallJump:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 128
+      buffer_size: 2048
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: linear
+    network_settings:
+      normalize: false
+      hidden_units: 256
+      num_layers: 2