Commit graph

28 commits

Author SHA1 Message Date
Sven Mika
357232d124
[Core/RLlib] Move log_once from rllib to ray.util. (#7273)
* Move log_once from rllib to tune.

* Move log_once from rllib to tune.

* LINT.

* Move to ray.util.debug.
2020-02-27 10:40:44 -08:00
Eric Liang
46af992efd
[rllib] [experimental] custom RL training pipelines (PG_pl, A2C_pl) (#7213) 2020-02-19 16:07:37 -08:00
Sven Mika
d537e9f0d8
[RLlib] Exploration API: merge deterministic flag with exploration classes (SoftQ and StochasticSampling). (#7155) 2020-02-19 12:18:45 -08:00
Eric Liang
5df801605e
Add ray.util package and move libraries from experimental (#7100) 2020-02-18 13:43:19 -08:00
Sven Mika
2e60f0d4d8
[RLlib] Move all jenkins RLlib-tests into bazel (rllib/BUILD). (#7178)
* commit

* comment
2020-02-15 14:50:44 -08:00
Eric Liang
026f6884b5
[rllib] Add Decentralized DDPPO trainer and documentation (#7088) 2020-02-10 15:28:27 -08:00
Sven Mika
6e1c3ea824
[RLlib] Exploration API (+EpsilonGreedy sub-class). (#6974) 2020-02-10 15:22:07 -08:00
Sven Mika
5ac5ac9560
[RLlib] Fix broken example: tf-eager with custom-RNN (#6732). (#7021)
* WIP.

* Fix float32 conversion in OneHot preprocessor (would cause float64 in eager, then NN-matmul-failure).
Add proper seq-len + state-in construction in eager_tf_policy.py::_compute_gradients().

* LINT.

* eager_tf_policy.py: Only set samples["seq_lens"] if RNN. Otherwise, eager-tracing will throw flattened-dict key-mismatch error.

* Move issue code to examples folder.

Co-authored-by: Eric Liang <ekhliang@gmail.com>
2020-02-06 09:44:08 -08:00
Eric Liang
fbc545c03b
[rllib] Support parallel, parameterized evaluation (#6981)
* eval api

* update

* sync eval filters

* sync fix

* docs

* update

* docs

* update

* link

* nit

* doc updates

* format
2020-02-01 22:12:12 -08:00
roireshef
3c60caa448
[rllib] implemented compute_advantages without gae (#6941) 2020-01-31 22:25:45 -08:00
roireshef
dc7a555260
[rllib] Feature/histograms in tensorboard (#6942)
* Added histogram functionality to custom metrics infrastructure (another tab in tensorboard)

* updated example to include histogram metric

* added histograms to TBXLogger

* add episode rewards

* lint

Co-authored-by: Eric Liang <ekhliang@gmail.com>
2020-01-30 22:02:53 -08:00
Eric Liang
2fb53396ad [rllib] [experimental] Decentralized Distributed PPO for torch (DD-PPO) (#6918) 2020-01-25 22:36:43 -08:00
Sven Mika
c957ed58ed [RLlib] Implement PPO torch version. (#6826) 2020-01-20 23:06:50 -08:00
Sven
60d4d5e1aa Remove future imports (#6724)
* Remove all __future__ imports from RLlib.

* Remove (object) again from tf_run_builder.py::TFRunBuilder.

* Fix 2xLINT warnings.

* Fix broken appo_policy import (must be appo_tf_policy)

* Remove future imports from all other ray files (not just RLlib).

* Remove future imports from all other ray files (not just RLlib).

* Remove future import blocks that contain `unicode_literals` as well.
Revert appo_tf_policy.py to appo_policy.py (belongs to another PR).

* Add two empty lines before Schedule class.

* Put back __future__ imports into determine_tests_to_run.py. Fails otherwise on a py2/print related error.
2020-01-09 00:15:48 -08:00
Robert Nishihara
39a3459886 Remove (object) from class declarations. (#6658) 2020-01-02 17:42:13 -08:00
Sven
f1b56fa5ee PG unify/cleanup tf vs torch and PG functionality test cases (tf + torch). (#6650)
* Unifying the code for PGTrainer/Policy wrt tf vs torch.
Adding loss function test cases for the PGAgent (confirm equivalence of tf and torch).

* Fix LINT line-len errors.

* Fix LINT errors.

* Fix `tf_pg_policy` imports (formerly: `pg_policy`).

* Rename tf_pg_... into pg_tf_... following <alg>_<framework>_... convention, where ...=policy/loss/agent/trainer.
Retire `PGAgent` class (use PGTrainer instead).

* - Move PG test into agents/pg/tests directory.
- All test cases will be located near the classes that are tested and
  then built into the Bazel/Travis test suite.

* Moved post_process_advantages into pg.py (from pg_tf_policy.py), b/c
the function is not a tf-specific one.

* Fix remaining import errors for agents/pg/...

* Fix circular dependency in pg imports.

* Add pg tests to Jenkins test suite.
2020-01-02 16:08:03 -08:00
Sven
8b16847c02 Get utils ready for better Agent torch support. (#6561) 2019-12-30 12:27:32 -08:00
Eric Liang
2530eb90dc
Move tf.test.is_gpu_available() to after session init (#6515)
* move to after session init

* script fixes
2019-12-17 14:55:39 -08:00
Eric Liang
4c6739476b
[rllib] Raise an error if GPUs are enabled but not tf.test.is_gpu_available() (#6365) 2019-12-05 10:13:54 -08:00
Eric Liang
ddc8855f41
Fix wrap (#6293) 2019-11-26 17:47:47 -08:00
gehring
8903bcd0c3 [rllib] Tracing for eager tensorflow policies with tf.function (#5705)
* Added tracing of eager policies with `tf.function`

* lint

* add config option

* add docs

* wip

* tracing now works with a3c

* typo

* none

* file doc

* returns

* syntax error

* syntax error
2019-09-17 01:44:20 -07:00
Eric Liang
daf38c8723
[tune] Deprecate tune.function (#5601)
* remove tune function

* remove examples

* Update tune-usage.rst
2019-08-31 16:00:10 -07:00
Eric Liang
03a1b75852
[rllib] Fix some eager execution regressions with 1.13 (#5537)
* fix bugs with 1.13

* allow disable
2019-08-26 23:23:35 -07:00
gehring
b520f6141e [rllib] Adds eager support with a generic TFEagerPolicy class (#5436) 2019-08-23 14:21:11 +08:00
Eric Liang
e2e30ca507 Ray, Tune, and RLlib support for memory, object_store_memory options (#5226) 2019-08-21 23:01:10 -07:00
Neil Lugovoy
1376f1ae60 [tune] Reporter crash fix (#5426)
Co-authored-by: Richard Liaw <rliaw@berkeley.edu>
2019-08-13 14:10:22 -07:00
Eric Liang
592f313210
[rllib] Centralized critic / PPO example on TwoStepGame (#5392) 2019-08-08 14:03:28 -07:00
Eric Liang
5d7afe8092
[rllib] Try moving RLlib to top level dir (#5324) 2019-08-05 23:25:49 -07:00