├── .github └── workflows │ ├── ci.yml │ └── pypi-publish.yml ├── .gitignore ├── .readthedocs.yaml ├── CONTRIBUTING.md ├── LICENSE ├── README.md ├── docs ├── .gitignore ├── Makefile ├── api.rst ├── conf.py ├── ext │ └── coverage_check.py └── index.rst ├── examples ├── __init__.py ├── experiment.py ├── online_q_lambda.py ├── online_q_learning.py ├── pop_art.py └── simple_dqn.py ├── pyproject.toml ├── rlax ├── __init__.py ├── _src │ ├── __init__.py │ ├── base.py │ ├── base_test.py │ ├── clipping.py │ ├── clipping_test.py │ ├── distributions.py │ ├── distributions_test.py │ ├── embedding.py │ ├── embedding_test.py │ ├── episodic_memory.py │ ├── episodic_memory_test.py │ ├── exploration.py │ ├── exploration_test.py │ ├── general_value_functions.py │ ├── general_value_functions_test.py │ ├── interruptions.py │ ├── interruptions_test.py │ ├── losses.py │ ├── losses_test.py │ ├── model_learning.py │ ├── model_learning_test.py │ ├── moving_averages.py │ ├── moving_averages_test.py │ ├── mpo_ops.py │ ├── mpo_ops_test.py │ ├── multistep.py │ ├── multistep_test.py │ ├── nested_updates.py │ ├── nested_updates_test.py │ ├── nonlinear_bellman.py │ ├── nonlinear_bellman_test.py │ ├── policy_gradients.py │ ├── policy_gradients_test.py │ ├── policy_targets.py │ ├── policy_targets_test.py │ ├── pop_art.py │ ├── pop_art_test.py │ ├── test_utils.py │ ├── transforms.py │ ├── transforms_test.py │ ├── tree_util.py │ ├── tree_util_test.py │ ├── value_learning.py │ ├── value_learning_test.py │ ├── vtrace.py │ └── vtrace_test.py └── rlax_test.py └── test.sh /.github/workflows/ci.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/.github/workflows/ci.yml -------------------------------------------------------------------------------- /.github/workflows/pypi-publish.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/.github/workflows/pypi-publish.yml -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/.gitignore -------------------------------------------------------------------------------- /.readthedocs.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/.readthedocs.yaml -------------------------------------------------------------------------------- /CONTRIBUTING.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/CONTRIBUTING.md -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/README.md -------------------------------------------------------------------------------- /docs/.gitignore: -------------------------------------------------------------------------------- 1 | _build 2 | -------------------------------------------------------------------------------- /docs/Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/docs/Makefile -------------------------------------------------------------------------------- /docs/api.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/docs/api.rst -------------------------------------------------------------------------------- /docs/conf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/docs/conf.py -------------------------------------------------------------------------------- /docs/ext/coverage_check.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/docs/ext/coverage_check.py -------------------------------------------------------------------------------- /docs/index.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/docs/index.rst -------------------------------------------------------------------------------- /examples/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/examples/__init__.py -------------------------------------------------------------------------------- /examples/experiment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/examples/experiment.py -------------------------------------------------------------------------------- /examples/online_q_lambda.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/examples/online_q_lambda.py -------------------------------------------------------------------------------- /examples/online_q_learning.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/examples/online_q_learning.py -------------------------------------------------------------------------------- /examples/pop_art.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/examples/pop_art.py -------------------------------------------------------------------------------- /examples/simple_dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/examples/simple_dqn.py -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/pyproject.toml -------------------------------------------------------------------------------- /rlax/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/__init__.py -------------------------------------------------------------------------------- /rlax/_src/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/__init__.py -------------------------------------------------------------------------------- /rlax/_src/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/base.py -------------------------------------------------------------------------------- /rlax/_src/base_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/base_test.py -------------------------------------------------------------------------------- /rlax/_src/clipping.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/clipping.py -------------------------------------------------------------------------------- /rlax/_src/clipping_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/clipping_test.py -------------------------------------------------------------------------------- /rlax/_src/distributions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/distributions.py -------------------------------------------------------------------------------- /rlax/_src/distributions_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/distributions_test.py -------------------------------------------------------------------------------- /rlax/_src/embedding.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/embedding.py -------------------------------------------------------------------------------- /rlax/_src/embedding_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/embedding_test.py -------------------------------------------------------------------------------- /rlax/_src/episodic_memory.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/episodic_memory.py -------------------------------------------------------------------------------- /rlax/_src/episodic_memory_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/episodic_memory_test.py -------------------------------------------------------------------------------- /rlax/_src/exploration.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/exploration.py -------------------------------------------------------------------------------- /rlax/_src/exploration_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/exploration_test.py -------------------------------------------------------------------------------- /rlax/_src/general_value_functions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/general_value_functions.py -------------------------------------------------------------------------------- /rlax/_src/general_value_functions_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/general_value_functions_test.py -------------------------------------------------------------------------------- /rlax/_src/interruptions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/interruptions.py -------------------------------------------------------------------------------- /rlax/_src/interruptions_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/interruptions_test.py -------------------------------------------------------------------------------- /rlax/_src/losses.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/losses.py -------------------------------------------------------------------------------- /rlax/_src/losses_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/losses_test.py -------------------------------------------------------------------------------- /rlax/_src/model_learning.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/model_learning.py -------------------------------------------------------------------------------- /rlax/_src/model_learning_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/model_learning_test.py -------------------------------------------------------------------------------- /rlax/_src/moving_averages.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/moving_averages.py -------------------------------------------------------------------------------- /rlax/_src/moving_averages_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/moving_averages_test.py -------------------------------------------------------------------------------- /rlax/_src/mpo_ops.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/mpo_ops.py -------------------------------------------------------------------------------- /rlax/_src/mpo_ops_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/mpo_ops_test.py -------------------------------------------------------------------------------- /rlax/_src/multistep.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/multistep.py -------------------------------------------------------------------------------- /rlax/_src/multistep_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/multistep_test.py -------------------------------------------------------------------------------- /rlax/_src/nested_updates.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/nested_updates.py -------------------------------------------------------------------------------- /rlax/_src/nested_updates_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/nested_updates_test.py -------------------------------------------------------------------------------- /rlax/_src/nonlinear_bellman.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/nonlinear_bellman.py -------------------------------------------------------------------------------- /rlax/_src/nonlinear_bellman_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/nonlinear_bellman_test.py -------------------------------------------------------------------------------- /rlax/_src/policy_gradients.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/policy_gradients.py -------------------------------------------------------------------------------- /rlax/_src/policy_gradients_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/policy_gradients_test.py -------------------------------------------------------------------------------- /rlax/_src/policy_targets.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/policy_targets.py -------------------------------------------------------------------------------- /rlax/_src/policy_targets_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/policy_targets_test.py -------------------------------------------------------------------------------- /rlax/_src/pop_art.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/pop_art.py -------------------------------------------------------------------------------- /rlax/_src/pop_art_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/pop_art_test.py -------------------------------------------------------------------------------- /rlax/_src/test_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/test_utils.py -------------------------------------------------------------------------------- /rlax/_src/transforms.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/transforms.py -------------------------------------------------------------------------------- /rlax/_src/transforms_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/transforms_test.py -------------------------------------------------------------------------------- /rlax/_src/tree_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/tree_util.py -------------------------------------------------------------------------------- /rlax/_src/tree_util_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/tree_util_test.py -------------------------------------------------------------------------------- /rlax/_src/value_learning.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/value_learning.py -------------------------------------------------------------------------------- /rlax/_src/value_learning_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/value_learning_test.py -------------------------------------------------------------------------------- /rlax/_src/vtrace.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/vtrace.py -------------------------------------------------------------------------------- /rlax/_src/vtrace_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/_src/vtrace_test.py -------------------------------------------------------------------------------- /rlax/rlax_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/rlax/rlax_test.py -------------------------------------------------------------------------------- /test.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/rlax/HEAD/test.sh --------------------------------------------------------------------------------