docs/references/q_functions.rst | |
|
|
docs/reproductions.rst | |
|
|
docs/requirements.txt | |
|
|
docs/software_design.rst | |
|
|
docs/tips.rst | |
|
|
docs/tutorials/after_training_policies.rst | |
|
|
docs/tutorials/create_your_dataset.rst | |
|
|
docs/tutorials/customize_neural_network.rst | |
|
|
docs/tutorials/data_collection.rst | |
|
|
docs/tutorials/finetuning.rst | |
|
|
docs/tutorials/getting_started.rst | |
|
|
docs/tutorials/index.rst | |
|
|
docs/tutorials/offline_policy_selection.rst | |
|
|
docs/tutorials/online_rl.rst | |
|
|
docs/tutorials/preprocess_and_postprocess.rst | |
|
|
docs/tutorials/use_distributional_q_function.rst | |
|
|
mypy.ini | |
|
|
pylintrc | |
|
|
requirements.txt | |
|
|
scripts/build-dist | |
|
|
scripts/build-docker | |
|
|
scripts/build-docs | |
|
|
scripts/create_cartpole_dataset | |
|
|
scripts/create_cartpole_random_dataset | |
|
|
scripts/create_pendulum_dataset | |
|
|
scripts/create_pendulum_random_dataset | |
|
|
scripts/format | |
|
|
scripts/lint | |
|
|
scripts/test | |
|
|
tutorials/atari.ipynb | |
|
|
tutorials/cartpole.ipynb | |
|
|
tutorials/online.ipynb | |
|
|
tutorials/tpu.ipynb | |
|
|
d3rlpy/__init__.py | 57 |
|
|
d3rlpy/_version.py | 1 |
|
|
d3rlpy/algos/__init__.py | 3 |
|
|
d3rlpy/algos/qlearning/__init__.py | 18 |
|
|
d3rlpy/algos/qlearning/awac.py | 139 |
|
|
d3rlpy/algos/qlearning/base.py | 746 |
|
|
d3rlpy/algos/qlearning/bc.py | 147 |
|
|
d3rlpy/algos/qlearning/bcq.py | 356 |
|
|
d3rlpy/algos/qlearning/bear.py | 236 |
|
|
d3rlpy/algos/qlearning/cal_ql.py | 152 |
|
|
d3rlpy/algos/qlearning/cql.py | 289 |
|
|
d3rlpy/algos/qlearning/crr.py | 168 |
|
|
d3rlpy/algos/qlearning/ddpg.py | 131 |
|
|
d3rlpy/algos/qlearning/dqn.py | 177 |
|
|
d3rlpy/algos/qlearning/explorers.py | 116 |
|
|
d3rlpy/algos/qlearning/iql.py | 151 |
|
|
d3rlpy/algos/qlearning/nfq.py | 93 |
|
|