Ervin Teng
4 年前
当前提交
985c80d7
共有 6 个文件被更改,包括 0 次插入 和 123 次删除
-
2ml-agents-envs/mlagents_envs/base_env.py
-
1ml-agents-envs/mlagents_envs/communicator_objects/agent_info_pb2.pyi
-
15ml-agents-envs/mlagents_envs/rpc_utils.py
-
14Project/Assets/ML-Agents/Examples/PushBlock/TFModels/PushBlockSuperNoEgo.onnx.meta
-
63config/ppo/WallJumpCollab.yaml
-
28config/ppo/Zombie.yaml
|
|||
fileFormatVersion: 2 |
|||
guid: b3b681e0364fd4b3e89015a1b23ac521 |
|||
ScriptedImporter: |
|||
fileIDToRecycleName: |
|||
11400000: main obj |
|||
11400002: model data |
|||
externalObjects: {} |
|||
userData: |
|||
assetBundleName: |
|||
assetBundleVariant: |
|||
script: {fileID: 11500000, guid: 683b6cb6d0a474744822c888b46772c9, type: 3} |
|||
optimizeModel: 1 |
|||
forceArbitraryBatchSize: 1 |
|||
treatErrorsAsWarnings: 0 |
|
|||
behaviors: |
|||
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: 15000000 |
|||
time_horizon: 128 |
|||
summary_freq: 20000 |
|||
threaded: true |
|||
environment_parameters: |
|||
big_wall_height: |
|||
curriculum: |
|||
- name: Lesson0 |
|||
completion_criteria: |
|||
measure: progress |
|||
behavior: SmallWallJump |
|||
signal_smoothing: true |
|||
min_lesson_length: 100 |
|||
threshold: 0.1 |
|||
value: 3 |
|||
- name: Lesson1 |
|||
completion_criteria: |
|||
measure: progress |
|||
behavior: SmallWallJump |
|||
signal_smoothing: true |
|||
min_lesson_length: 100 |
|||
threshold: 0.3 |
|||
value: 5 |
|||
- name: Lesson2 |
|||
completion_criteria: |
|||
measure: progress |
|||
behavior: SmallWallJump |
|||
signal_smoothing: true |
|||
min_lesson_length: 100 |
|||
threshold: 0.5 |
|||
value: 8 |
|||
- name: Lesson3 |
|||
completion_criteria: |
|||
measure: progress |
|||
behavior: SmallWallJump |
|||
signal_smoothing: true |
|||
min_lesson_length: 100 |
|||
threshold: 0.7 |
|||
value: 9 |
|||
- name: Lesson4 |
|||
value: 9 |
|
|||
behaviors: |
|||
PushBlock: |
|||
trainer_type: ppo |
|||
hyperparameters: |
|||
batch_size: 1024 |
|||
buffer_size: 10240 |
|||
learning_rate: 0.0003 |
|||
beta: 0.01 |
|||
epsilon: 0.2 |
|||
lambd: 0.95 |
|||
num_epoch: 3 |
|||
learning_rate_schedule: constant |
|||
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 #2000000 |
|||
time_horizon: 64 |
|||
summary_freq: 10000 |
|||
threaded: true |
|||
env_settings: |
|||
num_envs: 3 |
撰写
预览
正在加载...
取消
保存
Reference in new issue