* 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.
* WIP.
* Fix SAC.
* Fix SAC.
* Fix strange tf-error in ray core tests.
* Fix strange ray-core tf-error in test_memory_scheduling test case.
* Fix test_io.py.
* LINT.
* Update SAC yaml files' config.
Co-authored-by: Eric Liang <ekhliang@gmail.com>
* 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>
* 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>
* Add `RandomEnv` example to examples folder.
Convert warning into Error message when using an LSTM in a non-shared-vf network (after the warning, the program would crash).
* LINT.
* Fix issue #6884. LSTM + non-shared vf NN + PPO crashes when using a Tuple action space.
* LINT
* Change warning message for Model: shared_vf=False, LSTM=True cases.
* Bug fix.
* Add examples/random_env.py test to Jenkins.
* 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.
* 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.
* modify tf_policy to enable EntropyCoeffSchedule to handle list, and avoid negative values under current implementation
* Update custom_metrics_and_callbacks.py
* Update tf_policy.py
* custom action dist wip
* Test case for custom action dist
* ActionDistribution.get_parameter_shape_for_action_space pattern
* Edit exception message to also suggest using a custom action distribution
* Clean up ModelCatalog.get_action_dist
* Pass model config to ActionDistribution constructors
* Update custom action distribution test case
* Name fix
* Autoformatter
* parameter shape static methods for torch distributions
* Fix docstring
* Generalize fake array for graph initialization
* Fix action dist constructors
* Correct parameter shape static methods for multicategorical and gaussian
* Make suggested changes to custom action dist's
* Correct instances of not passing model config to action dist
* Autoformatter
* fix tuple distribution constructor
* bugfix
