102 次代码提交 (53185b7e-aeb9-4feb-b654-a3c441d91a19)

作者 SHA1 备注 提交日期
GitHub e92b4f88 [refactor] Structure configuration files into classes (#3936) 5 年前
Andrew Cohen 4464ca46 ignoring commit checks 5 年前
Andrew Cohen 91217b0d use settings.py to check PR config 5 年前
GitHub f5435876 [refactor] Store and restore state along with checkpoints (#4025) 5 年前
Andrew Cohen e7750fc9 Merge branch 'master' into develop-sampler-refactor 5 年前
GitHub 91f199cd Self play hyperparameter improvements (#4063) 5 年前
Andrew Cohen e386b829 some cleanups/ interval error checking 5 年前
Andrew Cohen 95898f37 using validator to check settings 5 年前
Andrew Cohen faced34d rename min value function check 5 年前
GitHub 09853e13 [refactor] Move checkpoint saving into trainer (#4034) 5 年前
Andrew Cohen 5ffd9761 type checks for parameter randomization settings/enforces float encoding 5 年前
Andrew Cohen b790ce76 error properly when a keyword is not followed by a valid config in yaml 5 年前
Andrew Cohen 7d52b18f seed each sampler individually 5 年前
Andrew Cohen e5c07272 using to_float for encoding 5 年前
Andrew Cohen c0f7052b Merge branch 'master' into develop-sampler-refactor 5 年前
GitHub a1c63c4b Release 3 Cherry-pick bug-fixes and doc changes from master (#4102) 5 年前
GitHub 8fb66c2d [bug-fix] Fix issue where curriculum was advancing too early (#4107) 5 年前
Andrew Cohen 953f4e09 from set_sampler_params => set_{samplertype}_params 5 年前
GitHub 5b0a5b9b Moving domain randomization to C# (#4065) 5 年前
yanchaosun 3ef4196e Added the algorithm named ppo_transfer 5 年前
Ervin Teng 510583d2 Move memory validation to settings 5 年前
yanchaosun ac4c80c2 integrate the implementation and hyperparameters 4 年前
yanchaosun 1e52ad3d ready for cloud training 4 年前
yanchaosun 05a96355 remove slim package 4 年前
yanchaosun 44fa16fa fix issues with cloud training 4 年前
GitHub a28e2767 Update add-fire to latest master, including Policy refactor (#4263) 4 年前
GitHub 93517833 [feature] Fix TF tests, add --torch CLI option, allow run TF without torch installed (#4305) 4 年前
Ruo-Ping Dong 6d67f857 move tf and add torch model serialization 4 年前
Andrew Cohen d5592462 add default settings 4 年前
yanchaosun d7402406 multiple sizes configs 4 年前
GitHub 3de1e660 [bug-fix] Initialize-from being incorrectly loaded as "None" rather than None (#4175) 5 年前
Ruo-Ping Dong 71fe4df6 fix formatting and test 4 年前
GitHub 0e0daf47 [add-fire] Merge post-0.19.0 master into add-fire (#4328) 4 年前
GitHub 839eb2cb Develop model transfer test (#4214) 4 年前
yanchaosun cdaaa318 bisim 4 年前
GitHub 8eefdcd3 Refactor of Curriculum and parameter sampling (#4160) 4 年前
GitHub e318f96a don't allow --num-envs >1 with no --env (#4203) 4 年前
Arthur Juliani c63b3d09 Fix lesson incrementing (#4279) 4 年前
yanchaosun 3246570c added action encoder, and flags related with action training/transferring; set model_schedule as a changable hyperparameter 4 年前
yanchaosun f81feec4 config fix; basic sac 4 年前
GitHub 380fef57 [refactor] Move TF-specific files to tf/ folder (#4266) 4 年前
yanchaosun 00bb821c fix sac transfer problems 4 年前
GitHub d1bf56e9 Fix lesson incrementing (#4279) 4 年前
yanchaosun 6df774ed update: separate model train as an option 4 年前
Andrew Cohen 598826fe Merge branch 'develop-add-fire' into develop-add-fire-bc 4 年前
Ruo-Ping Dong d3eb6c46 Merge branch 'develop-add-fire' into develop-add-fire-checkpoint 4 年前
Andrew Cohen ae2c83e2 added torch bc tests 4 年前
Andrew Cohen c25ddc5d fix tests 4 年前
GitHub 705a0e0e Curriculum: If no behavior specified, do magic (#4346) 4 年前
yanchaosun 3ce88589 1 layer everything 4 年前
GitHub 25dc8c3d Add Saver Class to handle all save/load/checkpoint/export work (#4323) 4 年前
Ervin Teng d65a9326 Merge branch 'master' into develop-add-fire-mm3 4 年前
GitHub 8985a040 Removing the experiment script from add fire (#4373) 4 年前
yanchaosun b5e02978 sac crawler config 4 年前
Anupam Bhatnagar e9d3de8e [skip ci] adding initializer 4 年前
Anupam Bhatnagar 0ca5ffcd [skip ci] fixing argument parser 4 年前
Anupam Bhatnagar 4d19245f [skip ci] adding PluginSettings 4 年前
Anupam Bhatnagar 3d82b7c2 [skip ci] adding action=DetectDefault in parser 4 年前
Anupam Bhatnagar dbd21c95 [skip ci] adding distributed trainers 4 年前
yanchaosun 2e927257 separate policy net 4 年前
GitHub df685184 Make --torch use torch even without config (#4400) 4 年前
Ruo-Ping Dong df8f1b88 use torch 4 年前
Scott Jordan d695c044 initial addition of active learning (incomplete) 4 年前
Anupam Bhatnagar f4f1a8d9 merge master into trainer-plugin branch 4 年前
Scott Jordan 56745026 Initial commit of running active learning code 4 年前
Anupam Bhatnagar d7f0d457 [skip ci] removing package import statements 4 年前
Scott Jordan 78f8a9a2 Updated task manager 4 年前
Scott Jordan cab9d77e Added Batch setting to active learning 4 年前
Scott Jordan cf2a06ad Added num repeat parameter for tasks 4 年前
Scott Jordan f9748b70 moved batch outside of active learner 4 年前
Scott Jordan d188890b fixed settings imports for active learning 4 年前
Scott Jordan e33168d6 Added comments and new yaml files for variable speed walker 4 年前
GitHub bf6506fc [feature] Add small CNN for grids 5x5 and up (#4434) 4 年前
yanchaosun 1a9aaaf6 model weights and large transfer learning weight 4 年前
GitHub 94c7111e [feature] Enable default settings for TrainerSettings (#4448) 4 年前
GitHub 60b76790 Random Network Distillation for Torch (#4473) 4 年前
GitHub efa2a704 add to_string for samplers (#4484) 4 年前
GitHub a690af74 [refactor] Make PyTorch the default and TensorFlow optional (#4517) 4 年前
Ervin Teng 3b15cc32 Multiprocessing but Stats are quite broken 4 年前
vincentpierre b863af57 Removing TensorFlow Trainers 4 年前
GitHub 14129a08 [MLA-470] Barracuda + TF cleanup (#4837) 4 年前
Andrew Cohen 1bc2ff96 add weight decay to trainers 4 年前
GitHub af5f6ad0 make sure DefaultTrainerDict is pickle-able (#4842) 4 年前
GitHub 457ed0b8 Set torch device from commandline (#4888) 4 年前
Arthur Juliani 7165e9cf Make conditiontype a setting 4 年前
GitHub 7954bd26 setuptools-based plugin for StatsWriters (#4788) 4 年前
Arthur Juliani 4413203d Sensor cleanup 4 年前
Christopher Goy 9cadfa7a Merge master -> release_13_branch-to-master 4 年前
Ervin Teng fd3f05b9 Enable GAIL to decay 4 年前
Ervin Teng 9bc88c41 Running COMA (not sure if learning) 4 年前
Ervin Teng c6904f86 Group reward function 4 年前
Ervin Teng 4b159789 Add PushBlockCollab config and fix some stuff 4 年前
Arthur Juliani 06c147f8 Merge remote-tracking branch 'origin/main' into goal-conditioning-new 4 年前
Arthur Juliani ce1d3d88 Resolve conflicts in networkbody 4 年前
GitHub f16ce486 Update v2-staging from main (March 15) (#5123) 4 年前
GitHub ba2af269 [coma2] Make group extrinsic reward part of extrinsic (#5033) 4 年前
GitHub 81705d6d Goal conditioning integration (#5142) 4 年前
GitHub 45e75e01 [config] Disable `threading` by default (#5221) 4 年前
vincentpierre 4e14879d Updating the barracuda 1.4.0 (#5291) 4 年前
GitHub 4995a765 [debug] Require all behavior names to have a matching YAML entry (#5210) 4 年前
vincentpierre 5985959d Got 2 modes on Wlker I think 4 年前
GitHub bb07eb45 Adding a fully connected visual encoder for super small visual input + tests (#5351) 4 年前