1
0
mirror of https://github.com/gryf/coach.git synced 2025-12-18 03:30:19 +01:00
Commit Graph

427 Commits

Author SHA1 Message Date
zach dwiel
f2fead57e5 change method interface: AgentInterface.emulate_act_on_trainer(transition: Transition) -> emulate_act_on_trainer(action: ActionType) 2019-04-09 12:14:27 -04:00
zach dwiel
b20e795ce0 create method LevelManager.acting_agent() 2019-04-09 12:14:27 -04:00
zach dwiel
54fdfe2da8 simplify rollout worker steps with new magic methods on StepMethod 2019-04-09 12:14:27 -04:00
zach dwiel
2cb078b4c2 add __truediv__, __rtruediv__ and __eq__ to StepMethod 2019-04-09 12:14:27 -04:00
zach dwiel
83da5cde2f remove unnecessary parentheses 2019-04-09 12:14:27 -04:00
zach dwiel
dddaefb210 fixed bug in rollout worker where total number of improved steps are not taken 2019-04-09 12:14:27 -04:00
zach dwiel
06de3b0f07 update LevelManager type signature 2019-04-09 12:14:27 -04:00
zach dwiel
f16cd3cb1e remove unused ActionInfo.action_intrinsic_reward 2019-04-09 12:14:27 -04:00
zach dwiel
7d79433c05 remove unused parameter scale_external_reward_by_intrinsic_reward_value 2019-04-09 12:14:27 -04:00
anabwan
881f78f45a tests: new checkpoint mxnet test + fix utils (#273)
* tests: new mxnet test + fix utils

new test added:
- test_restore_checkpoint[tensorflow, mxnet]

fix failed tests in CI
improve utils

* tests: fix comments for mxnet checkpoint test and utils
2019-04-07 07:36:44 +03:00
anabwan
e1e335a4ef disabled Starcraft from nightly (#286)
* disabled Starcraft from nightly

* tests: added comments
2019-04-04 22:26:25 +03:00
Zach Dwiel
2291cee2c6 allow serializing from/to arrays/str from GlobalVariableSaver (#285) 2019-04-04 11:09:19 -04:00
anabwan
cdb8d9e518 tests: fix multi environment variables in configci (#284)
* tests: fix multi environment variables in configci

- fix multi environment vairables in configci
- removing bitflip from mujoco tests
- add bitflip to gym

* tests: disable mujoco_a3c_lstm + fix timeout and fix docker
2019-04-04 16:11:41 +03:00
Scott Leishman
f173e69187 introduce dockerfiles. (#169)
* introduce dockerfiles.

* ensure golden tests are run not just collected.

* Skip CI download of dockerfiles.

* add StarCraft environment and tests.

* add minimaps starcraft validation parameters.

* Add functional test running (from Ayoob)

* pin mujoco_py version to a 1.5 compatible release.

* fix config syntax issue.

* pin remaining mujoco_py install calls.

* Relax pin of gym version in gym Dockerfile.

* update makefile based on functional test filtering.
2019-04-03 19:33:17 +03:00
shadiendrawis
0b808f0794 remove -ept flag (#283) 2019-04-03 16:32:24 +03:00
shadiendrawis
a543f10c1a fix Intel tensorflow installation issue (#281)
* fix intel tensorflow installation issue

* update version
2019-04-03 13:03:30 +03:00
anabwan
5d4b9c7399 added functional environments to CircleCI (#268)
added functional environments to CircleCI
2019-03-28 15:45:19 -07:00
anabwan
869bd421a3 tests: added new checkpoint and functional tests (#265)
* added new tests
- test_preset_n_and_ew
- test_preset_n_and_ew_and_onnx

* code utils improvements (all utils)
* improve checkpoint_test
* new functionality for functional_test markers and presets lists
* removed special environment container
* add xfail to certain tests
2019-03-28 13:57:31 -07:00
Gal Leibovich
310d31c227 integration test changes to reach the train part (#254)
* integration test changes to override heatup to 1000 steps +  run each preset for 30 sec (to make sure we reach the train part)

* fixes to failing presets uncovered with this change + changes in the golden testing to properly test BatchRL

* fix for rainbow dqn

* fix to gym_environment (due to a change in Gym 0.12.1) + fix for rainbow DQN + some bug-fix in utils.squeeze_list

* fix for NEC agent
2019-03-27 21:14:19 +02:00
Gal Leibovich
6e08c55ad5 Enabling-more-agents-for-Batch-RL-and-cleanup (#258)
allowing for the last training batch drawn to be smaller than batch_size + adding support for more agents in BatchRL by adding softmax with temperature to the corresponding heads + adding a CartPole_QR_DQN preset with a golden test + cleanups
2019-03-21 16:10:29 +02:00
Gal Leibovich
abec59f367 fixes to rainbow dqn + a cartpole based golden test (#253) 2019-03-21 12:57:56 +02:00
anabwan
83741fa92a tests: added function tests to nightly CircleCI (#252) 2019-03-20 15:39:22 -07:00
Gal Leibovich
e3c7e526c7 Batch RL (#238) 2019-03-19 18:07:09 +02:00
anabwan
4a8451ff02 tests: added new tests + utils code improved (#221)
* tests: added new tests + utils code improved

* new tests:
- test_preset_args_combination
- test_preset_mxnet_framework

* added more flags to test_preset_args
* added validation for flags in utils

* tests: added new tests + fixed utils

* tests: added new checkpoint test

* tests: added checkpoint test improve utils

* tests: added tests + improve validations

* bump integration CI run timeout.

* tests: improve timerun + add functional test marker
2019-03-18 11:21:43 +02:00
Gal Leibovich
d6158a5cfc restoring from a checkpoint file (#247) 2019-03-17 16:28:09 +02:00
shadiendrawis
f03bd7ad93 benchmark update (#250) 2019-03-17 15:33:28 +02:00
Nikhil Barhate
537b549e1d fixed broken url in README (#246) 2019-03-13 22:38:33 -07:00
Scott Leishman
9c449507e0 update CARLA install docs to note python client. (#234) 2019-03-13 22:21:44 -07:00
Gal Leibovich
8be9ea5dc9 Update setup.py (#245) 2019-03-12 11:08:10 +02:00
Gal Leibovich
c02333b1ba fix dashboard to allow connections from a remote machine. (#231) 2019-03-10 13:15:14 +02:00
Gal Leibovich
9a895a1ac7 bug-fix for l2_regularization not in use (#230)
* bug-fix for l2_regularization not in use
* removing not in use TF REGULARIZATION_LOSSES collection
2019-03-03 15:11:06 +02:00
Gal Novik
10220be9be Adding support for evaluation only mode with predefined number of steps (#225) 2019-03-03 10:03:45 +02:00
Ajay Deshpande
2c1a9dbf20 Adding framework for multinode tests (#149)
* Currently runs CartPole_ClippedPPO and Mujoco_ClippedPPO with inverted_pendulum level.
2019-02-26 13:53:12 -08:00
shadiendrawis
b461a1b8ab readme fix (#228) 2019-02-24 13:46:21 +02:00
shadiendrawis
2b5d1dabe6 ACER algorithm (#184)
* initial ACER commit

* Code cleanup + several fixes

* Q-retrace bug fix + small clean-ups

* added documentation for acer

* ACER benchmarks

* update benchmarks table

* Add nightly running of golden and trace tests. (#202)

Resolves #200

* comment out nightly trace tests until values reset.

* remove redundant observe ignore (#168)

* ensure nightly test env containers exist. (#205)

Also bump integration test timeout

* wxPython removal (#207)

Replacing wxPython with Python's Tkinter.
Also removing the option to choose multiple files as it is unused and causes errors, and fixing the load file/directory spinner.

* Create CONTRIBUTING.md (#210)

* Create CONTRIBUTING.md.  Resolves #188

* run nightly golden tests sequentially. (#217)

Should reduce resource requirements and potential CPU contention but increases
overall execution time.

* tests: added new setup configuration + test args (#211)

- added utils for future tests and conftest
- added test args

* new docs build

* golden test update
2019-02-20 23:52:34 +02:00
anabwan
7253f511ed tests: added new setup configuration + test args (#211)
- added utils for future tests and conftest
- added test args
2019-02-13 07:43:59 -05:00
Scott Leishman
9d0fed84a3 run nightly golden tests sequentially. (#217)
Should reduce resource requirements and potential CPU contention but increases
overall execution time.
2019-02-04 17:18:35 +02:00
Gal Novik
b4fd1b3c93 Create CONTRIBUTING.md (#210)
* Create CONTRIBUTING.md.  Resolves #188
2019-01-29 13:47:22 -08:00
Gal Novik
135f02fb46 wxPython removal (#207)
Replacing wxPython with Python's Tkinter.
Also removing the option to choose multiple files as it is unused and causes errors, and fixing the load file/directory spinner.
2019-01-23 20:49:37 +02:00
Scott Leishman
516547e3df ensure nightly test env containers exist. (#205)
Also bump integration test timeout
2019-01-18 13:43:42 -08:00
Cody Hsieh
bf0a65eefd remove redundant observe ignore (#168) 2019-01-17 14:08:05 -08:00
Scott Leishman
a048024bf5 Add nightly running of golden and trace tests. (#202)
Resolves #200

* comment out nightly trace tests until values reset.
2019-01-17 11:52:50 -08:00
Zach Dwiel
8672f8b542 Fix golden tests (#199)
* remove unused functions utils.read_json and utils.write_json
* increase verbosity of golden tests; detect errors in golden tests
2019-01-16 17:38:11 -08:00
Zach Dwiel
fedb4cbd7c Cleanup and refactoring (#171) 2019-01-15 10:04:53 +02:00
Zach Dwiel
cd812b0d25 more clear names for methods of Space (#181)
* rename Space.val_matches_space_definition -> contains; Space.is_point_in_space_shape -> valid_index
* rename valid_index -> is_valid_index
2019-01-14 15:02:53 -05:00
Zach Dwiel
0ccc333d77 raise value error if there is an invalid action space (#179) 2019-01-13 11:06:48 +02:00
Scott Leishman
053adf0ca9 prevent long job CI timeouts owing to lack of EKS token refresh (#183)
* add additional info during exception of eks runs.

* ensure we refresh k8s config after long calls.

Kubernetes client on EKS has a 10 minute token time to live, so will
result in unauthorized errors if tokens are not refreshed on long jobs.
2019-01-09 15:12:00 -08:00
Gal Novik
0fa9d8e602 Update README.md (#182) 2019-01-08 13:48:17 +02:00
Ajay Deshpande
8a1ea3d915 Merge pull request #161 from x77a1/master
Changes to avoid memory leak in Rollout worker
2019-01-03 21:15:04 -08:00
Gourav Roy
b1e9ea48d8 Refactored GlobalVariableSaver 2019-01-03 15:08:34 -08:00