gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2025-12-18 03:30:19 +01:00
Code Issues Projects Releases Wiki Activity
521 Commits 4 Branches 2 Tags
master
Commit Graph

298 Commits

Author SHA1 Message Date
Thom Lane
81bac050d7 Added Custom Initialisation for MXNet Heads (#86) 
* Added NormalizedRSSInitializer, using same method as TensorFlow backend, but changed name since ‘columns’ have different meaning in dense layer weight matrix in MXNet.

* Added unit test for NormalizedRSSInitializer.
 2018-11-16 08:15:43 -08:00
Balaji Subramaniam
101c55d37d Handle both Environment Steps and Episodes on the subscriber side. (#99) 2018-11-15 14:42:21 -08:00
Thom Lane
3358e04a6a Corrected MXNet's PPO Head for Continuous Action Spaces (#84) 
* Changes required for Continuous PPO Head with MXNet. Used in MountainCarContinuous_ClippedPPO.

* Simplified changes for continuous ppo.

* Cleaned up to avoid duplicate code, and simplified covariance creation.
 2018-11-15 13:27:54 -08:00
Ajay Deshpande
fde73ced13 Simulating the act on the trainer. (#65) 
* Remove the use of daemon threads for Redis subscribe.
* Emulate act and observe on trainer side to update internal vars.
 2018-11-15 08:38:58 -08:00
Itai Caspi
6d40ad1650 update of api docstrings across coach and tutorials [WIP] (#91) 
* updating the documentation website
* adding the built docs
* update of api docstrings across coach and tutorials 0-2
* added some missing api documentation
* New Sphinx based documentation
 2018-11-15 15:00:13 +02:00
Scott Leishman
524f8436a2 create per environment Dockerfiles. (#70) 
* create per environment Dockerfiles.

Adjust CI setup to better parallelize runs.
Fix a couple of issues in golden and trace tests.
Update a few of the docs.

* bugfix in mmc agent.

Also install kubectl for CI, update badge branch.

* remove integration test parallelism.
 2018-11-14 07:40:22 -08:00
Balaji Subramaniam
a849c17e46 Enable distributed SharedRunningStats (#81) 
- Use Redis pub/sub for updating SharedRunningStats.
 2018-11-13 19:17:38 +02:00
Ajay Deshpande
875d6ef017 Adding target reward and target sucess (#58) 
* Adding target reward

* Adding target successs

* Addressing comments

* Using custom_reward_threshold and target_success_rate

* Adding exit message

* Moving success rate to environment

* Making target_success_rate optional
 2018-11-12 15:03:43 -08:00
Itai Caspi
0fe583186e fixing the coach entrypoint after adding the CoachLauncher abstraction (#92) 2018-11-12 10:26:49 -08:00
Leo Dirac
2804a7c24f Refactor launcher to be object-oriented (#63) 
* Import of annoy library uses failed_import mechanism.
 2018-11-10 22:10:19 +02:00
Itai Caspi
3fd433ffab fix ddpg head (#78) 2018-11-09 08:17:04 -08:00
Itai Caspi
3a0a1159e9 fixing the dropout rate code (#72) 
addresses issue #53
 2018-11-08 16:53:47 +02:00
Itai Caspi
389c65cbbe fix for a bug in distributed training that was introduced lately (#75) 2018-11-08 16:52:48 +02:00
Itai Caspi
83e0b09a6a adding the missing export_onnx_graph parameter to task parameters (#73) 2018-11-08 12:52:42 +02:00
Leo Dirac
8f0415b4cc Tweak additional_simulator_parameters for easier configuration and better error logging. (#69) 2018-11-07 11:01:12 -08:00
Gal Leibovich
49dea39d34 N-step returns for rainbow (#67) 
* n_step returns for rainbow
* Rename CartPole_PPO -> CartPole_ClippedPPO
 2018-11-07 18:33:08 +02:00
Itai Caspi
35c477c922 allowing grayscale observations in gym (#66) 
* allowing grayscale observations in gym
 2018-11-07 17:08:10 +02:00
Sina Afrooze
5fadb9c18e Adding mxnet components to rl_coach/architectures (#60) 
Adding mxnet components to rl_coach architectures.

- Supports PPO and DQN
- Tested with CartPole_PPO and CarPole_DQN
- Normalizing filters don't work right now (see #49) and are disabled in CartPole_PPO preset
- Checkpointing is disabled for MXNet
 2018-11-07 17:07:15 +02:00
Itai Caspi
e7a91b4dc3 Fix cmd line arguments handling (#68) 
* refactoring the merging of the task parameters and the command line parameters
* removing some unused command line arguments
* fix for saving checkpoints when not passing through coach.py
 2018-11-07 15:47:02 +02:00
Sina Afrooze
93571306c3 Removed tensorflow specific code in presets (#59) 
* Add generic layer specification for using in presets

* Modify presets to use the generic scheme
 2018-11-06 17:39:29 +02:00
Itai Caspi
811152126c Export graph to ONNX (#61) 
Implements the ONNX graph exporting feature. 
Currently does not work for NAF, C51 and A3C_LSTM due to unsupported TF layers in the tf2onnx library.
 2018-11-06 10:55:21 +02:00
Leo Dirac
d75df17d97 Modifying ScreenLogger to optionally not output color codes (#56) 
* Modifying ScreenLogger to not output color when configured by new CLI parameter
 2018-11-05 15:25:49 -08:00
Balaji Subramaniam
7e7006305a Integrate coach.py params with distributed Coach. (#42) 
* Integrate coach.py params with distributed Coach.
* Minor improvements
- Use enums instead of constants.
- Reduce code duplication.
- Ask experiment name with timeout.
 2018-11-05 09:33:30 -08:00
Sina Afrooze
95b4fc6888 Added ability to switch between tensorflow and mxnet using -f commandline argument. (#48) 
NOTE: tensorflow framework works fine if mxnet is not installed in env, but mxnet will not work if tensorflow is not installed because of the code in network_wrapper.
 2018-10-30 15:29:34 -07:00
Sina Afrooze
2046358ab0 Add docstring for architecture (#47) 
- Removed get_model() from architecture because it is only implementation detail of architecture.
 2018-10-30 11:02:37 +02:00
Thom Lane
324c67d614 Bug fix: Removed reference to args which is out of scope. Conditioning now performed one level above. (#54) 2018-10-29 22:29:22 -07:00
Sina Afrooze
a888226641 Move embedder, middleware, and head parameters to framework agnostic modules. (#45) 
Part of #28
 2018-10-29 14:46:40 -07:00
Ajay Deshpande
16b3e99f37 Setup basic CI flow (#38) 
Adds automated running of unit, integration tests (and optionally longer running tests)
 2018-10-24 18:27:58 -07:00
Zach Dwiel
2cc6abc3c4 update CartPole_PPO not addressed during rebase (#41) 2018-10-24 16:58:25 -07:00
zach dwiel
f835ac902c fix renaming: save_checkpoint_sec -> checkpoint_save_secs 2018-10-24 10:52:18 -04:00
Ajay Deshpande
fb2721fffa Removing comments 2018-10-23 19:59:02 -04:00
Ajay Deshpande
9a30c26469 Adding improvements 2018-10-23 19:59:02 -04:00
zach dwiel
3ba0df7d07 update GraphManager.act specified return type 2018-10-23 19:58:17 -04:00
zach dwiel
def76b4cc6 update CartPole_PPO 2018-10-23 19:58:17 -04:00
zach dwiel
3e5e5475de update training worker 2018-10-23 19:58:17 -04:00
zach dwiel
430ca198e5 convert golden tests into pytest format 2018-10-23 19:58:17 -04:00
zach dwiel
787ab42578 remove extra call to super().store_episode 2018-10-23 19:58:17 -04:00
Zach Dwiel
7220283653 add len(Episode) 2018-10-23 19:58:17 -04:00
Zach Dwiel
700a175902 rename save_checkpoint_secs -> checkpoint_save_secs 2018-10-23 17:10:58 -04:00
Zach Dwiel
9804b033a2 rename save_checkpoint_dir -> checkpoint_save_dir 2018-10-23 17:10:58 -04:00
Zach Dwiel
201a2237a1 restructure looping mechanism inGraphManager 2018-10-23 17:10:58 -04:00
Zach Dwiel
52560a2aae introduce property GraphManager.current_step_counter 2018-10-23 17:10:04 -04:00
Zach Dwiel
776c94d551 reorder methods in GraphManager 2018-10-23 17:10:04 -04:00
Zach Dwiel
496a516de1 rename GraphManager.sync_graph -> sync 2018-10-23 17:08:29 -04:00
Zach Dwiel
5fee48dcfd remove argument keep_networks_in_sync from GraphManager.act, and move this feature into the only place that activated it: GraphManager.train_and_act 2018-10-23 17:08:29 -04:00
Zach Dwiel
b2d864a5bd remove out of date documentation 2018-10-23 17:08:29 -04:00
Zach Dwiel
d32d909238 move only invocation of GraphManager.handle_episode_ended inline 2018-10-23 17:08:29 -04:00
Zach Dwiel
18d84c5037 remove unnecessary timers from GraphManager 2018-10-23 16:58:17 -04:00
Zach Dwiel
cd30efe52e remove unnecessary test result is None in GraphManager.act 2018-10-23 16:57:43 -04:00
Zach Dwiel
35d67cbd9b use phase context in GraphManager.evaluate 2018-10-23 16:57:43 -04:00