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
13938 commits 227 branches 67 tags 234 MiB
Commit graph

230 commits

Author SHA1 Message Date
Sven Mika
f43d934817
[RLlib] Type annotations for policy. (#9248) 2020-07-05 13:09:51 +02:00
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
43043ee4d5
[RLlib] Tf2x preparation; part 2 (upgrading try_import_tf()). (#9136) 
* WIP.

* Fixes.

* LINT.

* WIP.

* WIP.

* Fixes.

* Fixes.

* Fixes.

* Fixes.

* WIP.

* Fixes.

* Test

* Fix.

* Fixes and LINT.

* Fixes and LINT.

* LINT.
 2020-06-30 10:13:20 +02:00
Sven Mika
0d37103f84
[RLlib] Prototype: Model Trajectory View API, part 0 (#9171) 2020-06-30 05:33:19 +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
Sven Mika
4fd8977eaf
[RLlib] Minor cleanup in preparation to tf2.x support. (#9130) 
* WIP.

* Fixes.

* LINT.

* Fixes.

* Fixes and LINT.

* WIP.
 2020-06-25 19:01:32 +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
14405b90d5
[RLlib] Prototype of a DynaTrainer (for env dynamics learning in upcoming MBMPO algo). (#8860) 2020-06-16 09:01:20 +02:00
Sven Mika
7008902cff
[RLlib] Minor rllib.utils cleanup. (#8932) 2020-06-16 08:52:20 +02:00
Eric Liang
34bae27ac7
[rllib] Flexible multi-agent replay modes and replay_sequence_length (#8893) 2020-06-12 20:17:27 -07:00
Sven Mika
0ba7472da9
[Testing] Fix LINT/sphinx errors. (#8874) 2020-06-10 15:41:59 +02:00
Eric Liang
831b2fe51d
[rllib] Set framework to tf by default and remove import checks; "Auto" option (#8748) 
* tf by default

* Update rllib/agents/trainer.py

Co-authored-by: Sven Mika <sven@anyscale.io>

* remove it

* fix

* remove

* fix

* lint

Co-authored-by: Sven Mika <sven@anyscale.io>
 2020-06-08 23:04:50 -07:00
Eric Liang
be26a7b1b0
[rllib] Support for complex / variable-length observation spaces (#8393) 2020-06-06 12:22:19 +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
Victor Le
aee01133cd
Fix dict/tuple hybrid action space for tensorflow eager execution (#8781) 2020-06-04 13:28:46 -07:00
Tanay Wakhare
c773824f4f
[RLlib] Bug fixes and tests in DiagGaussian (#8676) 2020-06-03 19:06:06 +02:00
Sven Mika
2746fc0476
[RLlib] Auto-framework, retire use_pytorch in favor of framework=... (#8520) 2020-05-27 16:19:13 +02:00
Sven Mika
6d196197bc
[RLlib] utils/spaces ... (#8608) 2020-05-27 10:21:30 +02:00
Sven Mika
0422e9c5a8
[RLlib] Add 2 Transformer learning test cases on StatelessCartPole (PPO and IMPALA). (#8624) 2020-05-27 10:19:47 +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
d946f58fd0
LINT fixes. (#8370) 2020-05-08 16:24:20 +02:00
gehring
7f14fb577d
[RLlib] Added TransformerXL and "stabilized for RL" variant, GTrXL (#6470) 2020-05-08 14:10:23 +02:00
Sven Mika
d7eaacb5fe
[RLlib] Issue 8319 DDPG (MA or num_envs_per_worker > 1) broken. (#8324) 2020-05-08 08:26:32 +02:00
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
eea75ac623
[RLlib] Beta distribution. (#8229) 2020-04-30 11:09:33 -07:00
Eric Liang
baadbdf8d4
[rllib] Execute PPO using training workflow (#8206) 
* wip

* add kl

* kl

* works now

* doc update

* reorg

* add ddppo

* add stats

* fix fetch

* comment

* fix learner stat regression

* test fixes

* fix test
 2020-04-30 01:18:09 -07:00
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
1775e89f26
[RLlib] Remove TupleActions and support arbitrarily nested action spaces. (#8143) 
Deprecate TupleActions and support arbitrarily nested action spaces.
Closes issue #8143.
 2020-04-28 14:59:16 +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
1d4823c0ec
[RLlib] Add testing framework_iterator. (#7852) 
* Add testing framework_iterator.

* LINT.

* WIP.

* Fix and LINT.

* LINT fix.
 2020-04-03 12:24:25 -07:00
Sven Mika
e153e3179f
[RLlib] Exploration API: Policy changes needed for forward pass noisifications. (#7798) 
* Rollback.

* WIP.

* WIP.

* 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.

* LINT.

* WIP.

Co-authored-by: Eric Liang <ekhliang@gmail.com>
 2020-04-01 00:43:21 -07:00
Sven Mika
66df8b8c35
[RLlib] Working/learning example: PPO + torch + LSTM. (#7797) 2020-03-31 22:00:28 -07:00
Sven Mika
1138f2ebed
[RLlib] Issue 7046 cannot restore keras model from h5 file. (#7482) 2020-03-23 12:19:30 -07:00
Sven Mika
20ef4a8603
[RLlib] Cleanup/unify all test cases. (#7533) 2020-03-11 20:39:47 -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
83e06cd30a
[RLlib] DDPG refactor and Exploration API action noise classes. (#7314) 
* WIP.

* WIP.

* WIP.

* WIP.

* WIP.

* Fix

* WIP.

* Add TD3 quick Pendulum regresison.

* Cleanup.

* Fix.

* LINT.

* Fix.

* Sort quick_learning test cases, add TD3.

* Sort quick_learning test cases, add TD3.

* Revert test_checkpoint_restore.py (debugging) changes.

* Fix old soft_q settings in documentation and test configs.

* More doc fixes.

* Fix test case.

* Fix test case.

* Lower test load.

* WIP.
 2020-03-01 11:53:35 -08:00
Matthew Brulhardt
75f683eec6
[rllib] Fix error in shape calculation. (#7301) 2020-02-25 14:16:29 -08:00