.gitignore
.pre-commit-config.yaml
CODE_OF_CONDUCT.md
CONTRIBUTING.md
LICENSE
MANIFEST.in
README.md
ROADMAP.md
mkdocs.yml
pyproject.toml
requirements.txt
setup.cfg
setup.py
.github/workflows/docs.yml
.github/workflows/pytest.yml
.github/workflows/python-publish.yml
docs/autoreset.md
docs/overview.md
docs/time_limits.md
docs/using_gather.md
docs/images/autoreset.png
docs/images/autoreset_nenvs.png
docs/images/bbrl_workspace.png
docs/images/gather_results.png
docs/images/noautoreset.png
docs/images/noautoreset_nenvs.png
docs/images/nsteps.png
docs/images/q_values_gather.png
docs/images/rl_agent.png
docs/images/transition_remove.png
docs/images/transition_reorganization.png
docs/images/transition_shifted_OK.png
docs/images/transition_shifted_missing.png
docs/learning_RL/a2c.md
docs/learning_RL/bias_variance.md
docs/learning_RL/ddpg.md
docs/learning_RL/dqn.md
docs/learning_RL/high_UTD.md
docs/learning_RL/learning_RL.md
docs/learning_RL/onp_ofp.md
docs/learning_RL/overview.md
docs/learning_RL/ppo.md
docs/learning_RL/reinforce.md
docs/learning_RL/sac.md
docs/learning_RL/tabular_dp.md
docs/learning_RL/tabular_mbrl.md
docs/learning_RL/tabular_mfrl.md
docs/learning_RL/trpo.md
docs/learning_RL/wrap_up.md
docs/notebooks/01-basic_concepts.student.ipynb
docs/notebooks/02-multi_env_noautoreset.student.ipynb
docs/notebooks/03-multi_env_autoreset.student.ipynb
documentation/bbrl/index.html
documentation/bbrl/workspace.html
documentation/bbrl/agents/agent.html
documentation/bbrl/agents/asynchronous.html
documentation/bbrl/agents/dataloader.html
documentation/bbrl/agents/gyma.html
documentation/bbrl/agents/gymb.html
documentation/bbrl/agents/index.html
documentation/bbrl/agents/remote.html
documentation/bbrl/agents/utils.html
documentation/bbrl/utils/chrono.html
documentation/bbrl/utils/functional.html
documentation/bbrl/utils/functionalb.html
documentation/bbrl/utils/index.html
documentation/bbrl/utils/logger.html
documentation/bbrl/utils/replay_buffer.html
documentation/bbrl/utils/utils.html
documentation/bbrl/visu/common.html
documentation/bbrl/visu/index.html
documentation/bbrl/visu/svpg_histograms.html
documentation/bbrl/visu/visu_critics.html
documentation/bbrl/visu/visu_policies.html
pdfs/2022/2022_SOTA.pdf
pdfs/2022/2022_pg.pdf
pdfs/2022/dp_2022.pdf
pdfs/2022/rld_intro.pdf
pdfs/2022/tab_rl_2022.pdf
pdfs/advanced/gcrl.pdf
pdfs/bbrl/bbrl_foundations.pdf
pdfs/deterministic/11_ddpg.pdf
pdfs/deterministic/Agent57.pdf
pdfs/deterministic/alpha0.pdf
pdfs/deterministic/alphaNPI.pdf
pdfs/deterministic/beyond_rainbow.pdf
pdfs/deterministic/ddpg.pdf
pdfs/deterministic/dp.pdf
pdfs/deterministic/dqn.pdf
pdfs/deterministic/hilbert.pdf
pdfs/deterministic/intro_rl.pdf
pdfs/deterministic/mcts.pdf
pdfs/deterministic/mcts_hilbert.pdf
pdfs/deterministic/mdp.pdf
pdfs/deterministic/off_policy_ddpg.pdf
pdfs/deterministic/ofp.pdf
pdfs/deterministic/ofp_correction.pdf
pdfs/deterministic/rb_mc_mbrl.pdf
pdfs/deterministic/rl.pdf
pdfs/ps/10_trpo_acktr.pdf
pdfs/ps/11_ppo.pdf
pdfs/ps/12_sac.pdf
pdfs/ps/13_rwr.pdf
pdfs/ps/14_wrap_up.pdf
pdfs/ps/1_ps_intro.pdf
pdfs/ps/2_ps_pb.pdf
pdfs/ps/3_pg_derivation1.pdf
pdfs/ps/4_pg_derivation2.pdf
pdfs/ps/5_pg_derivation3.pdf
pdfs/ps/6_baseline_AC.pdf
pdfs/ps/7_bias_variance.pdf
pdfs/ps/8_ofp.pdf
pdfs/ps/9_a2c.pdf
pdfs/ps/CS2621_TRPO_PPO.pdf
pdfs/ps/tqc.pdf
pdfs/regression/batch_lwr.pdf
pdfs/regression/batch_projec.pdf
pdfs/regression/gd_V2.pdf
pdfs/regression/grad_descent.pdf
pdfs/regression/intro_regression.pdf
pdfs/regression/iter_incr.pdf
pdfs/regression/lls.pdf
pdfs/regression/nn_reg.pdf
pdfs/regression/rbfn.pdf
pdfs/regression/robot_model_learning.pdf
src/bbrl/__init__.py
src/bbrl/_version.py
src/bbrl/stats.py
src/bbrl/test_transition.py
src/bbrl/workspace.py
src/bbrl.egg-info/PKG-INFO
src/bbrl.egg-info/SOURCES.txt
src/bbrl.egg-info/dependency_links.txt
src/bbrl.egg-info/requires.txt
src/bbrl.egg-info/top_level.txt
src/bbrl/agents/README.md
src/bbrl/agents/__init__.py
src/bbrl/agents/agent.py
src/bbrl/agents/asynchronous.py
src/bbrl/agents/dataloader.py
src/bbrl/agents/gymnasium.py
src/bbrl/agents/remote.py
src/bbrl/agents/seeding.py
src/bbrl/agents/utils.py
src/bbrl/utils/__init__.py
src/bbrl/utils/chrono.py
src/bbrl/utils/distributions.py
src/bbrl/utils/functional.py
src/bbrl/utils/logger.py
src/bbrl/utils/replay_buffer.py
src/bbrl/utils/utils.py
src/bbrl/utils/gymnasium/__init__.py
src/bbrl/utils/gymnasium/distributions.py
src/bbrl/visu/__init__.py
src/bbrl/visu/common.py
src/bbrl/visu/play.py
src/bbrl/visu/plot_critics.py
src/bbrl/visu/plot_policies.py
src/bbrl/visu/plot_trajectories.py
src/bbrl/visu/svpg_histograms.py
tests/eval_agent.py
tests/test_gymagent_continuous_cartpole.py
tests/test_gymagent_continuous_pendulum.py
tests/test_gymagent_continuous_pendulum_a.py
tests/test_gymagent_discrete_cartpole.py
tests/test_gymnasium.py
tests/test_rb.py
tests/utils/test_replay_buffer.py