hiro/ray
1
0
Fork 0
mirror of https://github.com/vale981/ray synced 2025-03-06 10:31:39 -05:00
Code Issues Projects Releases Packages Wiki Activity Actions
14010 commits 227 branches 67 tags 234 MiB
Commit graph

102 commits

Author SHA1 Message Date
Michael Luo
b2984d1c34
[RLlib] Model Annotations to Torch Models (#9749) 2020-11-12 12:16:12 +01:00
Sven Mika
291c172d83
[RLlib] Support Simplex action spaces for SAC (torch and tf). (#11909) 2020-11-11 18:45:28 +01:00
Jiajie Xiao
0b07af374a
allow tuple action space (#11429) 
Co-authored-by: Jiajie Xiao <jj@Jiajies-MBP-2.attlocal.net>
 2020-10-29 16:05:38 +01:00
Sven Mika
d9f1874e34
[RLlib] Minor fixes (torch GPU bugs + some cleanup). (#11609) 2020-10-27 10:00:24 +01:00
Sven Mika
d3bc20b727
[RLlib] ConvTranspose2D module (#11231) 2020-10-12 15:00:42 +02:00
Sven Mika
957877ad3f
Tf version of VisionNet (ray/rllib/model/tf/vision_net.py) crashes iff len(conv-filters)=1. (#11330) 2020-10-11 12:49:47 +02:00
Sven Mika
ce96b03b07
[RLlib] MB-MPO cleanup (comments, docstrings, type annotations). (#11033) 2020-10-06 20:28:16 +02:00
Sven Mika
36bda8432b
[RLlib] Trajectory view API: Simple List Collector (on by default for PPO); LSTM-agnostic (#11056) 2020-10-01 16:57:10 +02:00
Sven Mika
28ab797cf5
[RLlib] Deprecate old classes, methods, functions, config keys (in prep for RLlib 1.0). (#10544) 2020-09-06 10:58:00 +02:00
Sven Mika
e968b52cb7
[RLlib] Trajectory view API - 03 Fast LSTM + prev actions/rewards (#9950) 2020-08-21 12:35:16 +02:00
Sven Mika
2cbe29a7fa
[RLlib] Curiosity minor fixes, do-overs, and testing. (#10143) 2020-08-19 17:49:50 +02:00
Sven Mika
2256047876
[RLlib] Rename rllib.utils.types into typing to match built-in python module's name. (#10114) 2020-08-15 13:24:22 +02:00
Sven Mika
0effcda3e4
Add missing int-casts for all shape calculating code (using np.product([some shape])). (#10092) 2020-08-13 12:04:22 +02:00
Barak Michener
8e76796fd0
ci: Redo format.sh --all script & backfill lint fixes (#9956) 2020-08-07 16:49:49 -07:00
Sven Mika
5d5643e633
[RLlib] Add informative error message when bad Conv2D stack is used with fixed num_outputs (no flattening at end). (#9966) 2020-08-07 12:04:17 +02:00
Sven Mika
57690a3a9f
[RLlib] Trajectory view API - 02 actual API scaffold (#9753) 2020-08-06 10:54:20 +02:00
Sven Mika
5dc4b6686e
[RLlib] Implement DQN PyTorch distributional head. (#9589) 2020-07-25 09:29:24 +02:00
Eric Liang
590943a499
[rllib] Type annotations for model classes (#9646) 2020-07-24 12:01:46 -07:00
Raphael Avalos
5303c3abe3
Fix TorchDeterministic (#9241) 2020-07-23 10:43:20 -07:00
Sven Mika
5b2a97597b
[RLlib] Retire try_import_tree (should be installed along with other requirements). (#9211) 
- Retire try_import_tree.
- Stabilize test_supported_multi_agent.py.
 2020-07-02 13:06:34 +02:00
Sven Mika
5c6d5d4ab1
This PR fixes the currently broken lstm_use_prev_action_reward flag for default lstm models (model.use_lstm=True). (#8970) 2020-06-27 20:50:01 +02:00
Tanay Wakhare
f77c638d6d
Pytorch AttentionNet (#9088) 2020-06-23 20:42:30 +02:00
Sven Mika
2589309cf0
[RLlib] Make sure torch and tf behave the same wrt conv2d nets. (#8785) 2020-06-20 00:05:19 +02:00
Sven Mika
7008902cff
[RLlib] Minor rllib.utils cleanup. (#8932) 2020-06-16 08:52:20 +02:00
Sven Mika
0ba7472da9
[Testing] Fix LINT/sphinx errors. (#8874) 2020-06-10 15:41:59 +02:00
Sven Mika
c74dc58f8b
[RLlib] Fix use_lstm flag for ModelV2 (w/o ModelV1 wrapping) and add it for PyTorch. (#8734) 2020-06-05 15:40:30 +02:00
Tanay Wakhare
c773824f4f
[RLlib] Bug fixes and tests in DiagGaussian (#8676) 2020-06-03 19:06:06 +02:00
Sven Mika
6d196197bc
[RLlib] utils/spaces ... (#8608) 2020-05-27 10:21:30 +02:00
Sven Mika
796a834c48
[RLlib] Attention Net integration into ModelV2 and learning RL example. (#8371) 2020-05-18 17:26:40 +02:00
Sven Mika
5f4c196fed
[RLlib] Make PyTorch Model forward pass faster in vf-case. (#8422) 2020-05-14 10:15:50 +02:00
Eric Liang
7ce138a6dc
[rllib] Support free_log_std in ModelV2 (#8380) 
* update

* factor

* update

* fix test failures

* fix torch net
 2020-05-12 10:14:05 -07:00
Sven Mika
5f278c6411
[RLlib] Examples folder restructuring (models) part 1 (#8353) 2020-05-08 08:20:18 +02:00
Sven Mika
166bb5d690
[RLlib] IMPALA PyTorch (#8287) 
This PR adds an IMPALA PyTorch implementation.

- adds compilation tests for LSTM and w/o LSTM.
- adds learning test for CartPole.
 2020-05-03 13:44:25 +02:00
Sven Mika
bf25aee392
[RLlib] Deprecate all Model(v1) usage. (#8146) 
Deprecate all Model(v1) usage.
 2020-04-29 12:12:59 +02:00
Sven Mika
e9ee5c4e5f
[RLlib] Nested action space PR (minimally invasive; torch only + test). (#8101) 
- Add TorchMultiActionDistribution class.
- Add framework-agnostic test cases for TorchMultiActionDistribution.
 2020-04-23 09:09:22 +02:00
Sven Mika
d15609ba2a
[RLlib] PyTorch version of ARS (Augmented Random Search). (#8106) 
This PR implements a PyTorch version of RLlib's ARS algorithm using RLlib's functional algo builder API. It also adds a regression test for ARS (torch) on CartPole.
 2020-04-21 09:47:52 +02:00
Sven Mika
3812bfedda
[RLlib] PyTorch version of ES (Evolution Strategies). (#8104) 
PyTorch version of Evolution Strategies (ES) Algo.
 2020-04-20 21:47:28 +02:00
Sven Mika
165a86f1ab
[RLlib] SAC MuJoCo instability issues (tf and torch versions). (#8063) 
SAC (both torch and tf versions) are showing issues (crashes) due to numeric instabilities in the SquashedGaussian distribution (sampling + logp after extreme NN outputs).
This PR fixes these. Stable MuJoCo learning (HalfCheetah) has been confirmed on both tf and torch versions. A Distribution stability test (using extreme NN outputs) has been added for SquashedGaussian (can be used for any other type of distribution as well).
 2020-04-19 10:20:23 +02:00
Sven Mika
428516056a
[RLlib] SAC Torch (incl. Atari learning) (#7984) 
* Policy-classes cleanup and torch/tf unification.
- Make Policy abstract.
- Add `action_dist` to call to `extra_action_out_fn` (necessary for PPO torch).
- Move some methods and vars to base Policy
  (from TFPolicy): num_state_tensors, ACTION_PROB, ACTION_LOGP and some more.

* Fix `clip_action` import from Policy (should probably be moved into utils altogether).

* - Move `is_recurrent()` and `num_state_tensors()` into TFPolicy (from DynamicTFPolicy).
- Add config to all Policy c'tor calls (as 3rd arg after obs and action spaces).

* Add `config` to c'tor call to TFPolicy.

* Add missing `config` to c'tor call to TFPolicy in marvil_policy.py.

* Fix test_rollout_worker.py::MockPolicy and BadPolicy classes (Policy base class is now abstract).

* Fix LINT errors in Policy classes.

* Implement StatefulPolicy abstract methods in test cases: test_multi_agent_env.py.

* policy.py LINT errors.

* Create a simple TestPolicy to sub-class from when testing Policies (reduces code in some test cases).

* policy.py
- Remove abstractmethod from `apply_gradients` and `compute_gradients` (these are not required iff `learn_on_batch` implemented).
- Fix docstring of `num_state_tensors`.

* Make QMIX torch Policy a child of TorchPolicy (instead of Policy).

* QMixPolicy add empty implementations of abstract Policy methods.

* Store Policy's config in self.config in base Policy c'tor.

* - Make only compute_actions in base Policy's an abstractmethod and provide pass
implementation to all other methods if not defined.
- Fix state_batches=None (most Policies don't have internal states).

* Cartpole tf learning.

* Cartpole tf AND torch learning (in ~ same ts).

* Cartpole tf AND torch learning (in ~ same ts). 2

* Cartpole tf (torch syntax-broken) learning (in ~ same ts). 3

* Cartpole tf AND torch learning (in ~ same ts). 4

* Cartpole tf AND torch learning (in ~ same ts). 5

* Cartpole tf AND torch learning (in ~ same ts). 6

* Cartpole tf AND torch learning (in ~ same ts). Pendulum tf learning.

* WIP.

* WIP.

* SAC torch learning Pendulum.

* WIP.

* SAC torch and tf learning Pendulum and Cartpole after cleanup.

* WIP.

* LINT.

* LINT.

* SAC: Move policy.target_model to policy.device as well.

* Fixes and cleanup.

* Fix data-format of tf keras Conv2d layers (broken for some tf-versions which have data_format="channels_first" as default).

* Fixes and LINT.

* Fixes and LINT.

* Fix and LINT.

* WIP.

* Test fixes and LINT.

* Fixes and LINT.

Co-authored-by: Sven Mika <sven@Svens-MacBook-Pro.local>
 2020-04-15 13:25:16 +02:00
Sven Mika
1b31c11806
[RLlib] DDPG re-factor to fit into RLlib's functional algorithm builder API. (#7934) 2020-04-09 14:04:21 -07:00
Sven Mika
22ccc43670
[RLlib] DQN torch version. (#7597) 
* Fix.

* Rollback.

* WIP.

* WIP.

* WIP.

* WIP.

* WIP.

* WIP.

* WIP.

* WIP.

* Fix.

* Fix.

* Fix.

* Fix.

* Fix.

* WIP.

* WIP.

* Fix.

* Test case fixes.

* Test case fixes and LINT.

* Test case fixes and LINT.

* Rollback.

* WIP.

* WIP.

* Test case fixes.

* Fix.

* Fix.

* Fix.

* Add regression test for DQN w/ param noise.

* Fixes and LINT.

* Fixes and LINT.

* Fixes and LINT.

* Fixes and LINT.

* Fixes and LINT.

* Comment

* Regression test case.

* WIP.

* WIP.

* LINT.

* LINT.

* WIP.

* Fix.

* Fix.

* Fix.

* LINT.

* Fix (SAC does currently not support eager).

* Fix.

* WIP.

* LINT.

* Update rllib/evaluation/sampler.py

Co-Authored-By: Eric Liang <ekhliang@gmail.com>

* Update rllib/evaluation/sampler.py

Co-Authored-By: Eric Liang <ekhliang@gmail.com>

* Update rllib/utils/exploration/exploration.py

Co-Authored-By: Eric Liang <ekhliang@gmail.com>

* Update rllib/utils/exploration/exploration.py

Co-Authored-By: Eric Liang <ekhliang@gmail.com>

* WIP.

* WIP.

* Fix.

* LINT.

* LINT.

* Fix and LINT.

* WIP.

* WIP.

* WIP.

* WIP.

* Fix.

* LINT.

* Fix.

* Fix and LINT.

* Update rllib/utils/exploration/exploration.py

* Update rllib/policy/dynamic_tf_policy.py

Co-Authored-By: Eric Liang <ekhliang@gmail.com>

* Update rllib/policy/dynamic_tf_policy.py

Co-Authored-By: Eric Liang <ekhliang@gmail.com>

* Update rllib/policy/dynamic_tf_policy.py

Co-Authored-By: Eric Liang <ekhliang@gmail.com>

* Fixes.

* WIP.

* LINT.

* Fixes and LINT.

* LINT and fixes.

* LINT.

* Move action_dist back into torch extra_action_out_fn and LINT.

* Working SimpleQ learning cartpole on both torch AND tf.

* Working Rainbow learning cartpole on tf.

* Working Rainbow learning cartpole on tf.

* WIP.

* LINT.

* LINT.

* Update docs and add torch to APEX test.

* LINT.

* Fix.

* LINT.

* Fix.

* Fix.

* Fix and docstrings.

* Fix broken RLlib tests in master.

* Split BAZEL learning tests into cartpole and pendulum (reached the 60min barrier).

* Fix error_outputs option in BAZEL for RLlib regression tests.

* Fix.

* Tune param-noise tests.

* LINT.

* Fix.

* Fix.

* test

* test

* test

* Fix.

* Fix.

* WIP.

* WIP.

* WIP.

* WIP.

* LINT.

* WIP.

Co-authored-by: Eric Liang <ekhliang@gmail.com>
 2020-04-06 11:56:16 -07:00
Sven Mika
66df8b8c35
[RLlib] Working/learning example: PPO + torch + LSTM. (#7797) 2020-03-31 22:00:28 -07:00
Sven Mika
f08687f550
[RLlib] rllib train crashes when using torch PPO/PG/A2C. (#7508) 
* Fix.

* Rollback.

* TEST.

* TEST.

* TEST.

* TEST.

* TEST.

* TEST.

* TEST.

* TEST.

* TEST.

* TEST.

* TEST.

* TEST.

* TEST.

* TEST.

* TEST.

* TEST.

* TEST.

* TEST.

* TEST.

* TEST.

* TEST.

* TEST.

* TEST.
 2020-03-08 13:03:18 -07:00
Sven Mika
510c850651
[RLlib] SAC add discrete action support. (#7320) 
* Exploration API (+EpsilonGreedy sub-class).

* Exploration API (+EpsilonGreedy sub-class).

* Cleanup/LINT.

* Add `deterministic` to generic Trainer config (NOTE: this is still ignored by most Agents).

* Add `error` option to deprecation_warning().

* WIP.

* Bug fix: Get exploration-info for tf framework.
Bug fix: Properly deprecate some DQN config keys.

* WIP.

* LINT.

* WIP.

* Split PerWorkerEpsilonGreedy out of EpsilonGreedy.
Docstrings.

* Fix bug in sampler.py in case Policy has self.exploration = None

* Update rllib/agents/dqn/dqn.py

Co-Authored-By: Eric Liang <ekhliang@gmail.com>

* WIP.

* Update rllib/agents/trainer.py

Co-Authored-By: Eric Liang <ekhliang@gmail.com>

* WIP.

* Change requests.

* LINT

* In tune/utils/util.py::deep_update() Only keep deep_updat'ing if both original and value are dicts. If value is not a dict, set

* Completely obsolete syn_replay_optimizer.py's parameters schedule_max_timesteps AND beta_annealing_fraction (replaced with prioritized_replay_beta_annealing_timesteps).

* Update rllib/evaluation/worker_set.py

Co-Authored-By: Eric Liang <ekhliang@gmail.com>

* Review fixes.

* Fix default value for DQN's exploration spec.

* LINT

* Fix recursion bug (wrong parent c'tor).

* Do not pass timestep to get_exploration_info.

* Update tf_policy.py

* Fix some remaining issues with test cases and remove more deprecated DQN/APEX exploration configs.

* Bug fix tf-action-dist

* DDPG incompatibility bug fix with new DQN exploration handling (which is imported by DDPG).

* Switch off exploration when getting action probs from off-policy-estimator's policy.

* LINT

* Fix test_checkpoint_restore.py.

* Deprecate all SAC exploration (unused) configs.

* Properly use `model.last_output()` everywhere. Instead of `model._last_output`.

* WIP.

* Take out set_epsilon from multi-agent-env test (not needed, decays anyway).

* WIP.

* Trigger re-test (flaky checkpoint-restore test).

* WIP.

* WIP.

* Add test case for deterministic action sampling in PPO.

* bug fix.

* Added deterministic test cases for different Agents.

* Fix problem with TupleActions in dynamic-tf-policy.

* Separate supported_spaces tests so they can be run separately for easier debugging.

* LINT.

* Fix autoregressive_action_dist.py test case.

* Re-test.

* Fix.

* Remove duplicate py_test rule from bazel.

* LINT.

* WIP.

* WIP.

* SAC fix.

* SAC fix.

* WIP.

* WIP.

* WIP.

* FIX 2 examples tests.

* WIP.

* WIP.

* WIP.

* WIP.

* WIP.

* Fix.

* LINT.

* Renamed test file.

* WIP.

* Add unittest.main.

* Make action_dist_class mandatory.

* fix

* FIX.

* WIP.

* WIP.

* Fix.

* Fix.

* Fix explorations test case (contextlib cannot find its own nullcontext??).

* Force torch to be installed for QMIX.

* LINT.

* Fix determine_tests_to_run.py.

* Fix determine_tests_to_run.py.

* WIP

* Add Random exploration component to tests (fixed issue with "static-graph randomness" via py_function).

* Add Random exploration component to tests (fixed issue with "static-graph randomness" via py_function).

* Rename some stuff.

* Rename some stuff.

* WIP.

* update.

* WIP.

* Gumbel Softmax Dist.

* WIP.

* WIP.

* WIP.

* WIP.

* WIP.

* WIP.

* WIP

* WIP.

* WIP.

* Hypertune.

* Hypertune.

* Hypertune.

* Lock-in.

* Cleanup.

* LINT.

* Fix.

* Update rllib/policy/eager_tf_policy.py

Co-Authored-By: Kristian Hartikainen <kristian.hartikainen@gmail.com>

* Update rllib/agents/sac/sac_policy.py

Co-Authored-By: Kristian Hartikainen <kristian.hartikainen@gmail.com>

* Update rllib/agents/sac/sac_policy.py

Co-Authored-By: Kristian Hartikainen <kristian.hartikainen@gmail.com>

* Update rllib/models/tf/tf_action_dist.py

Co-Authored-By: Kristian Hartikainen <kristian.hartikainen@gmail.com>

* Update rllib/models/tf/tf_action_dist.py

Co-Authored-By: Kristian Hartikainen <kristian.hartikainen@gmail.com>

* Fix items from review comments.

* Add dm_tree to RLlib dependencies.

* Add dm_tree to RLlib dependencies.

* Fix DQN test cases ((Torch)Categorical).

* Fix wrong pip install.

Co-authored-by: Eric Liang <ekhliang@gmail.com>
Co-authored-by: Kristian Hartikainen <kristian.hartikainen@gmail.com>
 2020-03-06 10:37:12 -08:00
Sven Mika
4198db5038
Torch multicat support (7419) 2020-03-04 00:41:40 -08:00
Sven Mika
d8eeb96413
Fix issue with torch PPO not handling action spaces of shape=(>1,). (#7398) 2020-03-02 10:53:19 -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
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
Sven
8b16847c02 Get utils ready for better Agent torch support. (#6561) 2019-12-30 12:27:32 -08:00
Eric Liang
a1d2e17623
[rllib] Autoregressive action distributions (#5304) 2019-08-10 14:05:12 -07:00