Avnish Narayan
740def0a13
[RLlib] Put env-checker on critical path. ( #22191 )
2022-02-17 14:06:14 +01:00
Balaji Veeramani
7f1bacc7dc
[CI] Format Python code with Black ( #21975 )
...
See #21316 and #21311 for the motivation behind these changes.
2022-01-29 18:41:57 -08:00
Sven Mika
d5bfb7b7da
[RLlib] Preparatory PR for multi-agent multi-GPU learner (alpha-star style) #03 ( #21652 )
2022-01-25 14:16:58 +01:00
Artur Niederfahrenhorst
d07e50e957
[RLlib] Replay buffer API (cleanups; docstrings; renames; move into rllib/execution/buffers dir) ( #20552 )
2021-11-19 11:57:37 +01:00
Sven Mika
cf21c634a3
[RLlib] Fix deprecated warning for torch_ops.py (soft-replaced by torch_utils.py). ( #19982 )
2021-11-03 10:00:46 +01:00
Sven Mika
2d24ef0d32
[RLlib] Add all simple learning tests as framework=tf2. ( #19273 )
...
* Unpin gym and deprecate pendulum v0
Many tests in rllib depended on pendulum v0,
however in gym 0.21, pendulum v0 was deprecated
in favor of pendulum v1. This may change reward
thresholds, so will have to potentially rerun
all of the pendulum v1 benchmarks, or use another
environment in favor. The same applies to frozen
lake v0 and frozen lake v1
Lastly, all of the RLlib tests and Tune tests have
been moved to python 3.7
* fix tune test_sampler::testSampleBoundsAx
* fix re-install ray for py3.7 tests
Co-authored-by: avnishn <avnishn@uw.edu>
2021-11-02 12:10:17 +01:00
Sven Mika
1f0646f658
[RLlib] Issue 18418: SAC w/ dict space not working. ( #19101 )
2021-10-06 09:05:50 +02:00
Sven Mika
b4300dd532
[RLlib] Issue 18812: Torch multi-GPU stats not protected against race conditions. ( #18937 )
2021-10-04 13:29:00 +02:00
Sven Mika
ed85f59194
[RLlib] Unify all RLlib Trainer.train() -> results[info][learner][policy ID][learner_stats] and add structure tests. ( #18879 )
2021-09-30 16:39:05 +02:00
Sven Mika
9c9b482661
[RLlib] Allow n-step > 1 and prio. replay for R2D2 and RNNSAC. ( #18939 )
2021-09-29 21:31:34 +02:00
Sven Mika
e3e6ed7aaa
[RLlib] Issues 17844, 18034: Fix n-step > 1 bug. ( #18358 )
2021-09-06 12:14:20 +02:00
Sven Mika
599e589481
[RLlib] Move existing fake multi-GPU learning tests into separate buildkite job. ( #18065 )
2021-08-31 14:56:53 +02:00
Sven Mika
4888d7c9af
[RLlib] Replay buffers: Add config option to store contents in checkpoints. ( #17999 )
2021-08-31 12:21:49 +02:00
Sven Mika
924f11cd45
[RLlib] Torch algos use now-framework-agnostic MultiGPUTrainOneStep execution op (~33% speedup for PPO-torch + GPU). ( #17371 )
2021-08-03 11:35:49 -04:00
Sven Mika
8a844ff840
[RLlib] Issues: 17397, 17425, 16715, 17174. When on driver, Torch|TFPolicy should not use ray.get_gpu_ids() (b/c no GPUs assigned by ray). ( #17444 )
2021-08-02 17:29:59 -04:00
Julius Frost
d7a5ec1830
[RLlib] SAC tuple observation space fix ( #17356 )
2021-07-28 12:39:28 -04:00
Sven Mika
90b21ce27e
[RLlib] De-flake 3 test cases; Fix config.simple_optimizer and SampleBatch.is_training warnings. ( #17321 )
2021-07-27 14:39:06 -04:00
Sven Mika
5a313ba3d6
[RLlib] Refactor: All tf static graph code should reside inside Policy class. ( #17169 )
2021-07-20 14:58:13 -04:00
Sven Mika
bc09e75b78
[RLlib] Fix 3 flakey test cases. ( #15785 )
2021-05-16 12:20:33 +02:00
Sven Mika
bb8a286cbc
[RLlib] Support native tf.keras.Model (milestone toward obsoleting ModelV2 class). ( #14684 )
2021-04-27 10:44:54 +02:00
Sven Mika
cecfc3b43b
[RLlib] Multi-GPU support for Torch algorithms. ( #14709 )
2021-04-16 09:16:24 +02:00
Sven Mika
9c5a0cfd7a
[RLlib] Issue 14385: Policy.compute_actions_from_input_dict does not properly track accessed fields for Policy's view requirements. ( #14386 )
2021-04-11 18:20:04 +02:00
Raphael CHEN
93d4244d9c
[RLlib] Correctly get bytes size of SampleBatch ( #14801 )
2021-03-30 19:24:58 +02:00
Sven Mika
ef944bc5f0
[RLlib] Re-enable placement group support for RLlib. ( #14384 )
2021-03-05 08:16:24 +01:00
Richard Liaw
a2d2275ee1
Revert "[RLlib + Tune] Add placement group support to RLlib. ( #14289 )" ( #14360 )
...
This reverts commit 6cd0cd3bd9
2021-02-25 14:27:35 -08:00
Sven Mika
6cd0cd3bd9
[RLlib + Tune] Add placement group support to RLlib. ( #14289 )
2021-02-25 16:01:31 +01:00
Sven Mika
37c7daa3c0
[RLlib] DDPG: Support simplex action space. ( #14011 )
2021-02-10 15:10:01 +01:00
Sven Mika
52c94b7ee9
[RLlib] Allow SAC to use custom models as Q- or policy nets and deprecate "state-preprocessor" for image spaces. ( #13522 )
2021-02-02 13:05:58 +01:00
Sven Mika
b7dbbfbf41
[RLlib] Issue 11591: SAC loss does not use PR-weights in critic loss term. ( #12394 )
...
* WIP.
* Fix and LINT.
2020-11-25 11:28:46 -08:00
Sven Mika
62c7ab5182
[RLlib] Trajectory view API: Enable by default for PPO, IMPALA, PG, A3C (tf and torch). ( #11747 )
2020-11-12 16:27:34 +01:00
Sven Mika
291c172d83
[RLlib] Support Simplex action spaces for SAC (torch and tf). ( #11909 )
2020-11-11 18:45:28 +01:00
Sven Mika
d9f1874e34
[RLlib] Minor fixes (torch GPU bugs + some cleanup). ( #11609 )
2020-10-27 10:00:24 +01:00
Sven Mika
f5e2cda68a
[RLlib] SAC: log_alpha not being learnt when on GPU. ( #11298 )
2020-10-12 13:48:44 -07:00
Sven Mika
c17169dc11
[RLlib] Fix all example scripts to run on GPUs. ( #11105 )
2020-10-02 23:07:44 +02:00
Sven Mika
fcdf410ae1
[RLlib] Tf2.x native. ( #8752 )
2020-07-11 22:06:35 +02:00
Sven Mika
4da0e542d5
[RLlib] DDPG and SAC eager support (preparation for tf2.x) ( #9204 )
2020-07-08 16:12:20 +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
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
Sven Mika
4ed796a7d6
[RLlib] Add testing Policy.compute_single_action() for all agents. ( #8903 )
2020-06-13 17:51:50 +02:00
Eric Liang
9a83908c46
[rllib] Deprecate policy optimizers ( #8345 )
2020-05-21 10:16:18 -07:00
Sven Mika
754290daad
[RLlib] Add light-weight Trainer.compute_action() tests for all Algos. ( #8356 )
2020-05-08 16:31:31 +02:00
Eric Liang
b14cc16616
[rllib] Enable functional execution workflow API by default ( #8221 )
2020-05-05 12:36:42 -07:00
Sven Mika
7ec2223c84
[RLlib] DDPG PyTorch actor-model was missing sigmoid layer ( #8188 )
...
Fix DDPG PyTorch (missing sigmoid layer (to squash action outputs) after deterministic action outputs).
2020-04-26 23:08:13 +02:00
Sven Mika
f7e4dae852
[RLlib] DQN and SAC Atari benchmark fixes. ( #7962 )
...
* Add Atari SAC-discrete (learning MsPacman in 40k ts up to 780 rewards).
* SAC loss function test case fix.
2020-04-17 08:49:15 +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
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
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
