dopamine
Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.
File Explorer
Download Latest Version (.zip)- airraid.json
- airraid.vg.json
- airraid_CNN.json
- airraid_CNN.vg.json
- airraid_Impala.json
- airraid_Impala.vg.json
- alien.json
- alien.vg.json
- alien_CNN.json
- alien_CNN.vg.json
- alien_Impala.json
- alien_Impala.vg.json
- amidar.json
- amidar.vg.json
- amidar_CNN.json
- amidar_CNN.vg.json
- amidar_Impala.json
- amidar_Impala.vg.json
- assault.json
- assault.vg.json
- assault_CNN.json
- assault_CNN.vg.json
- assault_Impala.json
- assault_Impala.vg.json
- asterix.json
- asterix.vg.json
- asterix_CNN.json
- asterix_CNN.vg.json
- asterix_Impala.json
- asterix_Impala.vg.json
- asteroids.json
- asteroids.vg.json
- asteroids_CNN.json
- asteroids_CNN.vg.json
- asteroids_Impala.json
- asteroids_Impala.vg.json
- atlantis.json
- atlantis.vg.json
- atlantis_CNN.json
- atlantis_CNN.vg.json
- atlantis_Impala.json
- atlantis_Impala.vg.json
- bankheist.json
- bankheist.vg.json
- bankheist_CNN.json
- bankheist_CNN.vg.json
- bankheist_Impala.json
- bankheist_Impala.vg.json
- battlezone.json
- battlezone.vg.json
- battlezone_CNN.json
- battlezone_CNN.vg.json
- battlezone_Impala.json
- battlezone_Impala.vg.json
- beamrider.json
- beamrider.vg.json
- beamrider_CNN.json
- beamrider_CNN.vg.json
- beamrider_Impala.json
- beamrider_Impala.vg.json
- berzerk.json
- berzerk.vg.json
- berzerk_CNN.json
- berzerk_CNN.vg.json
- berzerk_Impala.json
- berzerk_Impala.vg.json
- bowling.json
- bowling.vg.json
- bowling_CNN.json
- bowling_CNN.vg.json
- bowling_Impala.json
- bowling_Impala.vg.json
- boxing.json
- boxing.vg.json
- boxing_CNN.json
- boxing_CNN.vg.json
- boxing_Impala.json
- boxing_Impala.vg.json
- breakout.json
- breakout.vg.json
- breakout_CNN.json
- breakout_CNN.vg.json
- breakout_Impala.json
- breakout_Impala.vg.json
- carnival.json
- carnival.vg.json
- carnival_CNN.json
- carnival_CNN.vg.json
- carnival_Impala.json
- carnival_Impala.vg.json
- centipede.json
- centipede.vg.json
- centipede_CNN.json
- centipede_CNN.vg.json
- centipede_Impala.json
- centipede_Impala.vg.json
- choppercommand.json
- choppercommand.vg.json
- choppercommand_CNN.json
- choppercommand_CNN.vg.json
- choppercommand_Impala.json
- choppercommand_Impala.vg.json
- crazyclimber.json
- crazyclimber.vg.json
- crazyclimber_CNN.json
- crazyclimber_CNN.vg.json
- crazyclimber_Impala.json
- crazyclimber_Impala.vg.json
- demonattack.json
- demonattack.vg.json
- demonattack_CNN.json
- demonattack_CNN.vg.json
- demonattack_Impala.json
- demonattack_Impala.vg.json
- doubledunk.json
- doubledunk.vg.json
- doubledunk_CNN.json
- doubledunk_CNN.vg.json
- doubledunk_Impala.json
- doubledunk_Impala.vg.json
- elevatoraction.json
- elevatoraction.vg.json
- elevatoraction_CNN.json
- elevatoraction_CNN.vg.json
- elevatoraction_Impala.json
- elevatoraction_Impala.vg.json
- enduro.json
- enduro.vg.json
- enduro_CNN.json
- enduro_CNN.vg.json
- enduro_Impala.json
- enduro_Impala.vg.json
- fishingderby.json
- fishingderby.vg.json
- fishingderby_CNN.json
- fishingderby_CNN.vg.json
- fishingderby_Impala.json
- fishingderby_Impala.vg.json
- freeway.json
- freeway.vg.json
- freeway_CNN.json
- freeway_CNN.vg.json
- freeway_Impala.json
- freeway_Impala.vg.json
- frostbite.json
- frostbite.vg.json
- frostbite_CNN.json
- frostbite_CNN.vg.json
- frostbite_Impala.json
- frostbite_Impala.vg.json
- gopher.json
- gopher.vg.json
- gopher_CNN.json
- gopher_CNN.vg.json
- gopher_Impala.json
- gopher_Impala.vg.json
- gravitar.json
- gravitar.vg.json
- gravitar_CNN.json
- gravitar_CNN.vg.json
- gravitar_Impala.json
- gravitar_Impala.vg.json
- hero.json
- hero.vg.json
- hero_CNN.json
- hero_CNN.vg.json
- hero_Impala.json
- hero_Impala.vg.json
- icehockey.json
- icehockey.vg.json
- icehockey_CNN.json
- icehockey_CNN.vg.json
- icehockey_Impala.json
- icehockey_Impala.vg.json
- jamesbond.json
- jamesbond.vg.json
- jamesbond_CNN.json
- jamesbond_CNN.vg.json
- jamesbond_Impala.json
- jamesbond_Impala.vg.json
- journeyescape.json
- journeyescape.vg.json
- journeyescape_CNN.json
- journeyescape_CNN.vg.json
- journeyescape_Impala.json
- journeyescape_Impala.vg.json
- kangaroo.json
- kangaroo.vg.json
- kangaroo_CNN.json
- kangaroo_CNN.vg.json
- kangaroo_Impala.json
- kangaroo_Impala.vg.json
- krull.json
- krull.vg.json
- krull_CNN.json
- krull_CNN.vg.json
- krull_Impala.json
- krull_Impala.vg.json
- kungfumaster.json
- kungfumaster.vg.json
- kungfumaster_CNN.json
- kungfumaster_CNN.vg.json
- kungfumaster_Impala.json
- kungfumaster_Impala.vg.json
- montezumarevenge.json
- montezumarevenge.vg.json
- montezumarevenge_CNN.json
- montezumarevenge_CNN.vg.json
- montezumarevenge_Impala.json
- montezumarevenge_Impala.vg.json
- mspacman.json
- mspacman.vg.json
- mspacman_CNN.json
- mspacman_CNN.vg.json
- mspacman_Impala.json
- mspacman_Impala.vg.json
- namethisgame.json
- namethisgame.vg.json
- namethisgame_CNN.json
- namethisgame_CNN.vg.json
- namethisgame_Impala.json
- namethisgame_Impala.vg.json
- phoenix.json
- phoenix.vg.json
- phoenix_CNN.json
- phoenix_CNN.vg.json
- phoenix_Impala.json
- phoenix_Impala.vg.json
- pitfall.json
- pitfall.vg.json
- pitfall_CNN.json
- pitfall_CNN.vg.json
- pitfall_Impala.json
- pitfall_Impala.vg.json
- pong.json
- pong.vg.json
- pong_CNN.json
- pong_CNN.vg.json
- pong_Impala.json
- pong_Impala.vg.json
- pooyan.json
- pooyan.vg.json
- pooyan_CNN.json
- pooyan_CNN.vg.json
- pooyan_Impala.json
- pooyan_Impala.vg.json
- privateeye.json
- privateeye.vg.json
- privateeye_CNN.json
- privateeye_CNN.vg.json
- privateeye_Impala.json
- privateeye_Impala.vg.json
- qbert.json
- qbert.vg.json
- qbert_CNN.json
- qbert_CNN.vg.json
- qbert_Impala.json
- qbert_Impala.vg.json
- riverraid.json
- riverraid.vg.json
- riverraid_CNN.json
- riverraid_CNN.vg.json
- riverraid_Impala.json
- riverraid_Impala.vg.json
- roadrunner.json
- roadrunner.vg.json
- roadrunner_CNN.json
- roadrunner_CNN.vg.json
- roadrunner_Impala.json
- roadrunner_Impala.vg.json
- robotank.json
- robotank.vg.json
- robotank_CNN.json
- robotank_CNN.vg.json
- robotank_Impala.json
- robotank_Impala.vg.json
- seaquest.json
- seaquest.vg.json
- seaquest_CNN.json
- seaquest_CNN.vg.json
- seaquest_Impala.json
- seaquest_Impala.vg.json
- skiing.json
- skiing.vg.json
- skiing_CNN.json
- skiing_CNN.vg.json
- skiing_Impala.json
- skiing_Impala.vg.json
- solaris.json
- solaris.vg.json
- solaris_CNN.json
- solaris_CNN.vg.json
- solaris_Impala.json
- solaris_Impala.vg.json
- spaceinvaders.json
- spaceinvaders.vg.json
- spaceinvaders_CNN.json
- spaceinvaders_CNN.vg.json
- spaceinvaders_Impala.json
- spaceinvaders_Impala.vg.json
- stargunner.json
- stargunner.vg.json
- stargunner_CNN.json
- stargunner_CNN.vg.json
- stargunner_Impala.json
- stargunner_Impala.vg.json
- tennis.json
- tennis.vg.json
- tennis_CNN.json
- tennis_CNN.vg.json
- tennis_Impala.json
- tennis_Impala.vg.json
- timepilot.json
- timepilot.vg.json
- timepilot_CNN.json
- timepilot_CNN.vg.json
- timepilot_Impala.json
- timepilot_Impala.vg.json
- tutankham.json
- tutankham.vg.json
- tutankham_CNN.json
- tutankham_CNN.vg.json
- tutankham_Impala.json
- tutankham_Impala.vg.json
- upndown.json
- upndown.vg.json
- upndown_CNN.json
- upndown_CNN.vg.json
- upndown_Impala.json
- upndown_Impala.vg.json
- venture.json
- venture.vg.json
- venture_CNN.json
- venture_CNN.vg.json
- venture_Impala.json
- venture_Impala.vg.json
- videopinball.json
- videopinball.vg.json
- videopinball_CNN.json
- videopinball_CNN.vg.json
- videopinball_Impala.json
- videopinball_Impala.vg.json
- wizardofwor.json
- wizardofwor.vg.json
- wizardofwor_CNN.json
- wizardofwor_CNN.vg.json
- wizardofwor_Impala.json
- wizardofwor_Impala.vg.json
- yarsrevenge.json
- yarsrevenge.vg.json
- yarsrevenge_CNN.json
- yarsrevenge_CNN.vg.json
- yarsrevenge_Impala.json
- yarsrevenge_Impala.vg.json
- zaxxon.json
- zaxxon.vg.json
- zaxxon_CNN.json
- zaxxon_CNN.vg.json
- zaxxon_Impala.json
- zaxxon_Impala.vg.json
- legacy_plots.html
- plots.html
- README.md
- ant.json
- ant.vg.json
- halfcheetah.json
- halfcheetah.vg.json
- hopper.json
- hopper.vg.json
- humanoid.json
- humanoid.vg.json
- walker2d.json
- walker2d.vg.json
- plots.html
- README.md
- plots.html
- README.md
- Dockerfile
- Dockerfile
- Dockerfile
- README.md
- DQNAgent.md
- dqn_agent.md
- ImplicitQuantileAgent.md
- implicit_quantile_agent.md
- project_distribution.md
- RainbowAgent.md
- rainbow_agent.md
- dqn.md
- implicit_quantile.md
- rainbow.md
- get_latest_file.md
- get_latest_iteration.md
- load_baselines.md
- load_statistics.md
- read_experiment.md
- summarize_data.md
- utils.md
- ContinuousRunner.md
- ContinuousTrainRunner.md
- create_continuous_agent.md
- create_continuous_runner.md
- run_experiment.md
- AtariPreprocessing.md
- create_atari_environment.md
- GameOverWrapper.md
- ImplicitQuantileNetwork.md
- NatureDQNNetwork.md
- RainbowNetwork.md
- Checkpointer.md
- get_latest_checkpoint_number.md
- AcrobotDQNNetwork.md
- AcrobotFourierDQNNetwork.md
- AcrobotRainbowNetwork.md
- BasicDiscreteDomainNetwork.md
- CartpoleDQNNetwork.md
- CartpoleFourierDQNNetwork.md
- CartpoleRainbowNetwork.md
- create_gym_environment.md
- FourierBasis.md
- FourierDQNNetwork.md
- GymPreprocessing.md
- LunarLanderDQNNetwork.md
- MountainCarDQNNetwork.md
- IterationStatistics.md
- acrobot_dqn_network.md
- acrobot_fourier_dqn_network.md
- acrobot_rainbow_network.md
- cartpole_dqn_network.md
- cartpole_fourier_dqn_network.md
- cartpole_rainbow_network.md
- fourier_dqn_network.md
- implicit_quantile_network.md
- nature_dqn_network.md
- rainbow_network.md
- Logger.md
- create_agent.md
- create_runner.md
- load_gin_configs.md
- Runner.md
- TrainRunner.md
- atari_lib.md
- checkpointer.md
- gym_lib.md
- iteration_statistics.md
- legacy_networks.md
- logger.md
- run_experiment.md
- train.md
- JaxDQNAgent.md
- dqn_agent.md
- JaxFullRainbowAgent.md
- full_rainbow_agent.md
- JaxImplicitQuantileAgent.md
- implicit_quantile_agent.md
- PPOAgent.md
- ppo_agent.md
- JaxQuantileAgent.md
- quantile_agent.md
- JaxRainbowAgent.md
- project_distribution.md
- rainbow_agent.md
- SACAgent.md
- sac_agent.md
- dqn.md
- full_rainbow.md
- implicit_quantile.md
- ppo.md
- quantile.md
- rainbow.md
- sac.md
- Checkpointable.md
- Checkpointer.md
- CheckpointHandler.md
- ActorCriticNetwork.md
- ActorCriticOutput.md
- ActorNetwork.md
- ActorOutput.md
- CriticNetwork.md
- CriticOutput.md
- PPOActorCriticNetwork.md
- PPOActorCriticOutput.md
- PPOActorNetwork.md
- PPOActorOutput.md
- PPOCriticNetwork.md
- PPOCriticOutput.md
- huber_loss.md
- mse_loss.md
- softmax_cross_entropy_loss_with_logits.md
- ClassicControlDQNNetwork.md
- ClassicControlRainbowNetwork.md
- feature_layer.md
- FourierBasis.md
- FullRainbowNetwork.md
- ImpalaDQNNetwork.md
- ImpalaEncoder.md
- ImplicitQuantileNetwork.md
- JaxFourierDQNNetwork.md
- NatureDQNNetwork.md
- NoisyNetwork.md
- PPOActorNetwork.md
- PPOCriticNetwork.md
- PPODiscreteActorCriticNetwork.md
- PPOSharedNetwork.md
- preprocess_atari_inputs.md
- QuantileNetwork.md
- RainbowNetwork.md
- Stack.md
- Accumulator.md
- TransitionAccumulator.md
- compress.md
- ReplayElement.md
- ReplayElementProtocol.md
- TransitionElement.md
- uncompress.md
- ReplayBuffer.md
- PrioritizedSampleMetadata.md
- PrioritizedSamplingDistribution.md
- SampleMetadata.md
- SamplingDistribution.md
- SequentialSamplingDistribution.md
- UniformSamplingDistribution.md
- SumTree.md
- accumulator.md
- elements.md
- replay_buffer.md
- samplers.md
- sum_tree.md
- decode.md
- encode.md
- LongIntegerEncoding.md
- NumpyEncoding.md
- agents.md
- checkpointers.md
- continuous_networks.md
- losses.md
- networks.md
- replay_memory.md
- serialization.md
- atari_100k_rainbow_agent.md
- ppo_cale.md
- sac_cale.md
- utils.md
- dqn_moe_agent.md
- full_rainbow_moe_agent.md
- losses.md
- rainbow_100k_moe_agent.md
- types.md
- moe.md
- networks.md
- routers.md
- softmoe.md
- types.md
- agents.md
- architectures.md
- google.md
- continuous_networks.md
- deepmind_control_lib.md
- atari_100k.md
- cale.md
- moes.md
- sac_from_pixels.md
- Collector.md
- add_collector.md
- CollectorDispatcher.md
- ConsoleCollector.md
- PickleCollector.md
- StatisticsInstance.md
- TensorboardCollector.md
- collector.md
- collector_dispatcher.md
- console_collector.md
- pickle_collector.md
- statistics_instance.md
- tensorboard_collector.md
- OutOfGraphReplayBuffer.md
- WrappedReplayBuffer.md
- OutOfGraphPrioritizedReplayBuffer.md
- WrappedPrioritizedReplayBuffer.md
- circular_replay_buffer.md
- prioritized_replay_buffer.md
- sum_tree.md
- DQNAgent.md
- dqn_agent.md
- ImplicitQuantileAgent.md
- implicit_quantile_agent.md
- project_distribution.md
- RainbowAgent.md
- rainbow_agent.md
- dqn.md
- implicit_quantile.md
- rainbow.md
- OutOfGraphReplayBuffer.md
- ReplayElement.md
- WrappedReplayBuffer.md
- OutOfGraphPrioritizedReplayBuffer.md
- WrappedPrioritizedReplayBuffer.md
- SumTree.md
- circular_replay_buffer.md
- prioritized_replay_buffer.md
- sum_tree.md
- agents.md
- replay_memory.md
- AgentVisualizer.md
- AtariPlotter.md
- BarPlotter.md
- create_runner.md
- LinePlotter.md
- Plotter.md
- agent_visualizer.md
- atari_plotter.md
- bar_plotter.md
- example_viz.md
- example_viz_lib.md
- line_plotter.md
- plotter.md
- _api_cache.json
- _redirects.yaml
- _toc.yaml
- agents.md
- all_symbols.md
- api_report.pb
- colab.md
- continuous_domains.md
- discrete_domains.md
- jax.md
- labs.md
- metrics.md
- replay_memory.md
- tf.md
- utils.md
- _toc.yaml
- dopamine.md
- index.md
- agents.md
- changelist.md
- README.md
- __init__.py
- agent_visualizer.ipynb
- agents.ipynb
- cartpole.ipynb
- jax_agent_visualizer.ipynb
- load_statistics.ipynb
- README.md
- tensorboard.ipynb
- utils.py
- __init__.py
- run_experiment.py
- train.py
- __init__.py
- atari_lib.py
- checkpointer.py
- gym_lib.py
- iteration_statistics.py
- legacy_networks.py
- logger.py
- run_experiment.py
- train.py
- dqn.gin
- dqn_acrobot.gin
- dqn_cartpole.gin
- dqn_fourier_acrobot.gin
- dqn_fourier_cartpole.gin
- dqn_fourier_lunarlander.gin
- dqn_fourier_mountaincar.gin
- dqn_lunarlander.gin
- dqn_mountaincar.gin
- dqn_profiling.gin
- __init__.py
- dqn_agent.py
- full_rainbow.gin
- full_rainbow_profiling.gin
- __init__.py
- full_rainbow_agent.py
- implicit_quantile.gin
- implicit_quantile_profiling.gin
- __init__.py
- implicit_quantile_agent.py
- ppo.gin
- ppo_atari.gin
- __init__.py
- ppo_agent.py
- quantile.gin
- quantile_profiling.gin
- __init__.py
- quantile_agent.py
- c51.gin
- c51_acrobot.gin
- c51_cartpole.gin
- c51_lunarlander.gin
- c51_mountaincar.gin
- c51_profiling.gin
- rainbow.gin
- rainbow_acrobot.gin
- rainbow_cartpole.gin
- rainbow_lunarlander.gin
- rainbow_mountaincar.gin
- rainbow_profiling.gin
- __init__.py
- rainbow_agent.py
- sac.gin
- __init__.py
- sac_agent.py
- __init__.py
- __init__.py
- accumulator.py
- elements.py
- replay_buffer.py
- samplers.py
- sum_tree.py
- __init__.py
- checkpointers.py
- continuous_networks.py
- losses.py
- networks.py
- README.md
- serialization.py
- DER.gin
- DrQ.gin
- DrQ_eps.gin
- OTRainbow.gin
- SPR.gin
- deterministic_sum_tree.py
- subsequence_replay_buffer.py
- __init__.py
- atari_100k_rainbow_agent.py
- atari_100k_runner.py
- eval_run_experiment.py
- normalization_utils.py
- README.md
- spr_agent.py
- spr_networks.py
- train.py
- ppo_cale.gin
- ppo_cale_100k.gin
- sac_cale.gin
- sac_cale_100k.gin
- __init__.py
- networks.py
- ppo_cale.py
- sac_cale.py
- utils.py
- __init__.py
- brax_lib.py
- sac_brax.gin
- train.py
- __init__.py
- dqn_asterix.gin
- dqn_breakout.gin
- dqn_freeway.gin
- dqn_seaquest.gin
- dqn_space_invaders.gin
- minatar_env.py
- quantile_asterix.gin
- quantile_breakout.gin
- quantile_freeway.gin
- quantile_seaquest.gin
- quantile_space_invaders.gin
- rainbow_asterix.gin
- rainbow_breakout.gin
- rainbow_freeway.gin
- rainbow_seaquest.gin
- rainbow_space_invaders.gin
- __init__.py
- __init__.py
- dqn_moe_agent.py
- full_rainbow_moe_agent.py
- losses.py
- rainbow_100k_moe_agent.py
- types.py
- __init__.py
- moe.py
- networks.py
- routers.py
- softmoe.py
- types.py
- DER.gin
- dqn.gin
- dqn_acrobot_moe.gin
- dqn_cartpole_moe.gin
- dqn_impala.gin
- dqn_lunarlander_moe.gin
- dqn_mountaincar_moe.gin
- full_rainbow.gin
- __init__.py
- atari_100k_train.py
- README.md
- jax_classy_cql.gin
- jax_dqn.gin
- jax_dr3.gin
- jax_rainbow.gin
- jax_return_conditioned_bc.gin
- networks.py
- offline_classy_cql_agent.py
- offline_dqn_agent.py
- offline_dr3_agent.py
- offline_rainbow_agent.py
- return_conditioned_bc_agent.py
- run_experiment.py
- train.py
- scaling_dataset_utils.py
- tfds_atari_utils.py
- tfds_replay.py
- __init__.py
- fixed_replay.py
- dqn_dense.gin
- DrQ_eps_dense.gin
- rainbow_dense.gin
- sac_mujoco_dense_config.gin
- sac_train_eval.py
- __init__.py
- networks.py
- recycled_atari100k_rainbow_agent.py
- recycled_dqn_agents.py
- recycled_rainbow_agent.py
- train.py
- weight_recyclers.py
- __init__.py
- continuous_networks.py
- deepmind_control_lib.py
- README.md
- sac_pixels.gin
- __init__.py
- README.md
- requirements.txt
- run.sh
- run_experiment.py
- tandem_dqn_agent.py
- train.py
- __init__.py
- __init__.py
- collector.py
- collector_dispatcher.py
- console_collector.py
- pickle_collector.py
- statistics_instance.py
- tensorboard_collector.py
- dqn.gin
- dqn_acrobot.gin
- dqn_cartpole.gin
- dqn_icml.gin
- dqn_lunarlander.gin
- dqn_mountaincar.gin
- dqn_nature.gin
- dqn_profiling.gin
- __init__.py
- dqn_agent.py
- implicit_quantile.gin
- implicit_quantile_icml.gin
- implicit_quantile_profiling.gin
- __init__.py
- implicit_quantile_agent.py
- c51.gin
- c51_acrobot.gin
- c51_cartpole.gin
- c51_icml.gin
- c51_profiling.gin
- rainbow.gin
- rainbow_aaai.gin
- rainbow_acrobot.gin
- rainbow_cartpole.gin
- rainbow_profiling.gin
- __init__.py
- rainbow_agent.py
- __init__.py
- __init__.py
- circular_replay_buffer.py
- prioritized_replay_buffer.py
- sum_tree.py
- __init__.py
- __init__.py
- agent_visualizer.py
- atari_plotter.py
- bar_plotter.py
- example_viz.py
- example_viz_lib.py
- line_plotter.py
- plotter.py
- test_utils.py
- __init__.py
- all_asterix_tb.png
- c51_asterix_tb.png
- dopamine_logo.png
- run_experiment_test.py
- atari_lib_test.py
- checkpointer_test.py
- gym_lib_test.py
- iteration_statistics_test.py
- logger_test.py
- run_experiment_test.py
- dqn_agent_test.py
- full_rainbow_agent_test.py
- implicit_quantile_agent_test.py
- ppo_agent_test.py
- quantile_agent_test.py
- rainbow_agent_test.py
- sac_agent_test.py
- accumulator_test.py
- elements_test.py
- replay_buffer_regression_test.py
- replay_buffer_test.py
- samplers_test.py
- sum_tree_test.py
- checkpointers_test.py
- continuous_networks_test.py
- losses_test.py
- networks_test.py
- serialization_test.py
- train_test.py
- networks_test.py
- offline_agent_test.py
- continuous_networks_test.py
- deepmind_control_lib_test.py
- collector_dispatcher_test.py
- collector_test.py
- console_collector_test.py
- pickle_collector_test.py
- tensorboard_collector_test.py
- gin_config_test.py
- integration_test.py
- train_runner_integration_test.py
- dqn_agent_test.py
- implicit_quantile_agent_test.py
- rainbow_agent_test.py
- circular_replay_buffer_test.py
- prioritized_replay_buffer_test.py
- sum_tree_test.py
- agent_visualizer_test.py
- atari_init_test.py
- AUTHORS
- CONTRIBUTING.md
- LICENSE
- README.md
- requirements.txt
- setup.py
π Installation Guide
1. Get the code
git clone https://github.com/google/dopamine
Downloads the entire project code from GitHub to your computer.
cd dopamine
Moves into the project folder you just downloaded.
2. Official Install Script
Easy RecommendedPrerequisites
- Python 3 Python is required to use pip.
pip install dopamine-rl
Installs the package published on PyPI directly β no need to clone the source.
After installing, open a new terminal and run the program's version command (e.g. --version) to confirm it worked.
Pulled directly from this repo's README.
3. Docker
EasyPrerequisites
- Git Needed to download the project code from GitHub.
- Docker Desktop Needed to build and run containers. Install it and keep it running in the background.
docker build -f docker/atari/Dockerfile -t dopamine .
Builds a runnable image based on the Dockerfile.
docker run -p 8080:80 dopamine
Runs the built image as an actual container.
Run docker compose ps to check the containers are Up. If the README mentions a port, open http://localhost:PORT in your browser.
4. Python
EasyPrerequisites
pip install -r dopamine/requirements.txt
Installs the Python libraries listed in requirements.txt (or similar).
pip install dopamine-rl
Installs the package published on PyPI directly β no need to clone the source.
python -m tests.dopamine.atari_init_test
Runs the Python script (or module).
If it runs without errors and prints output in the terminal, it worked.
Pulled directly from this repo's README.
// repository documentation
Was this content helpful?
(0 ratings)
