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
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
53206dd440
[RLlib] CQL BC loss fixes; PPO/PG/A2|3C action normalization fixes ( #16531 )
2021-06-30 12:32:11 +02:00
Sven Mika
d0014cd351
[RLlib] Policies get/set_state fixes and enhancements. ( #16354 )
2021-06-15 13:08:43 +02:00
Sven Mika
2d34216660
[RLlib] APEX-DQN: Bug fix for torch and add learning test. ( #15762 )
2021-05-20 09:27:03 +02:00
Sven Mika
16ddab49f5
[RLlib] Trainer._evaluate -> Trainer.evaluate; Also make evaluation possible w/o evaluation worker set. ( #15591 )
2021-05-12 12:16:00 +02:00
Sven Mika
e973b726c2
[RLlib] Support native tf.keras.Models (part 2) - Default keras models for Vision/RNN/Attention. ( #15273 )
2021-04-30 19:26:30 +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
732197e23a
[RLlib] Multi-GPU for tf-DQN/PG/A2C. ( #13393 )
2021-03-08 15:41:27 +01:00
Sven Mika
8000258333
[RLlib] R2D2 Implementation. ( #13933 )
2021-02-25 12:18:11 +01:00
Sven Mika
775e685531
[RLlib] Issue #13824 : compress_observations=True crashes for all algos not using a replay buffer. ( #14034 )
2021-02-18 21:36:32 +01:00
Sven Mika
dab241dcc6
[RLlib] Fix inconsistency wrt batch size in SampleCollector (traj. view API). Makes DD-PPO work with traj. view API. ( #12063 )
2020-11-19 19:01:14 +01:00
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
5dc4b6686e
[RLlib] Implement DQN PyTorch distributional head. ( #9589 )
2020-07-25 09:29:24 +02:00
Sven Mika
fcdf410ae1
[RLlib] Tf2.x native. ( #8752 )
2020-07-11 22:06:35 +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
4ed796a7d6
[RLlib] Add testing Policy.compute_single_action() for all agents. ( #8903 )
2020-06-13 17:51:50 +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
d8a081a185
[RLlib] Unity3D integration (n Unity3D clients vs learning server). ( #8590 )
2020-05-30 22:48:34 +02:00
Sven Mika
2746fc0476
[RLlib] Auto-framework, retire use_pytorch in favor of framework=... ( #8520 )
2020-05-27 16:19:13 +02:00
Eric Liang
9d012626e5
[rllib] Distributed exec workflow for impala ( #8321 )
2020-05-11 20:24:43 -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
Sven Mika
b95e28faea
[RLlib] APEX_DDPG (PyTorch) test case and docs. ( #8288 )
...
APEX_DDPG (PyTorch) test case and docs.
2020-05-04 09:36:27 +02:00
Eric Liang
2298f6fb40
[rllib] Port DQN/Ape-X to training workflow api ( #8077 )
2020-04-23 12:39:19 -07:00
Sven Mika
d6cb7d865e
[RLlib] Torch DQN (APEX) TD-Error/prio. replay fixes. ( #8082 )
...
PyTorch APEX_DQN with Prioritized Replay enabled would not work properly due to the td_error not being retrievable by the AsyncReplayOptimizer.
2020-04-20 10:03:25 +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
82c2d9faba
[RLlib] Fix broken RLlib tests in master. ( #7894 )
2020-04-05 09:34:23 -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
5537fe13b0
[RLlib] Exploration API: ParamNoise Integration into DQN; working example/test cases. ( #7814 )
2020-04-03 10:44:25 -07:00
Sven Mika
e4bd5db4d8
[RLlib] Minimal ParamNoise PR. ( #7772 )
2020-03-28 16:16:30 -07:00
Sven Mika
93b5c38b7d
[RLlib] Noisy layers in DQN throw different errors (issue #7635 ). ( #7750 )
...
* Rollback.
* Fix issue 7635.
* Fix issue 7635.
* LINT and bug fix.
2020-03-26 22:08:34 -07:00
Eric Liang
be48e1964b
[rllib] Fix per-worker exploration in Ape-X; make more kwargs required for future safety ( #7504 )
...
* fix sched
* lintc
* lint
* fix
* add unit test
* fix
* format
* fix test
* fix test
2020-03-10 11:14:14 -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
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
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 Mika
6e1c3ea824
[RLlib] Exploration API (+EpsilonGreedy sub-class). ( #6974 )
2020-02-10 15:22:07 -08:00
