acme
A library of reinforcement learning components and agents
File Explorer
Download Latest Version (.zip)- ci.yml
- release.yml
- __init__.py
- base.py
- episode.py
- episode_test.py
- sequence.py
- sequence_test.py
- structured.py
- structured_test.py
- test_cases.py
- test_utils.py
- transition.py
- transition_test.py
- utils.py
- __init__.py
- base.py
- wrappers.py
- __init__.py
- builder.py
- builder_test.py
- config.py
- dac.py
- gail.py
- learning.py
- learning_test.py
- losses.py
- losses_test.py
- networks.py
- README.md
- rewards.py
- __init__.py
- builder.py
- config.py
- learning.py
- networks.py
- README.md
- __init__.py
- agent_test.py
- builder.py
- config.py
- learning.py
- losses.py
- networks.py
- pretraining.py
- pretraining_test.py
- README.md
- __init__.py
- builder.py
- config.py
- losses.py
- networks.py
- README.md
- __init__.py
- agent_test.py
- builder.py
- config.py
- learning.py
- networks.py
- README.md
- __init__.py
- agent_test.py
- builder.py
- config.py
- learning.py
- losses.py
- networks.py
- README.md
- __init__.py
- builder.py
- config.py
- learning.py
- networks.py
- README.md
- __init__.py
- actor.py
- builder.py
- config.py
- learning.py
- learning_lib.py
- losses.py
- networks.py
- rainbow.py
- README.md
- __init__.py
- acting.py
- builder.py
- config.py
- learning.py
- networks.py
- types.py
- __init__.py
- builder.py
- config.py
- lfd_adder.py
- lfd_adder_test.py
- sacfd.py
- td3fd.py
- __init__.py
- acting.py
- agent_test.py
- builder.py
- config.py
- dataset.py
- dataset_test.py
- ensemble.py
- ensemble_test.py
- learning.py
- losses.py
- models.py
- mppi.py
- mppi_test.py
- networks.py
- README.md
- __init__.py
- acting.py
- builder.py
- categorical_mpo.py
- config.py
- learning.py
- networks.py
- README.md
- rollout_loss.py
- types.py
- utils.py
- __init__.py
- actor.py
- builder.py
- config.py
- factories.py
- learner_set.py
- README.md
- __init__.py
- __init__.py
- builder.py
- config.py
- learning.py
- networks.py
- normalization.py
- README.md
- __init__.py
- adder.py
- builder.py
- config.py
- README.md
- rewarder.py
- __init__.py
- actor.py
- builder.py
- config.py
- learning.py
- networks.py
- __init__.py
- builder.py
- config.py
- learning.py
- networks.py
- README.md
- __init__.py
- builder.py
- config.py
- learning.py
- networks.py
- README.md
- __init__.py
- builder.py
- builder_test.py
- README.md
- __init__.py
- builder.py
- config.py
- learning.py
- networks.py
- README.md
- __init__.py
- builder.py
- config.py
- learning.py
- networks.py
- README.md
- __init__.py
- acting.py
- builder.py
- config.py
- learning.py
- networks.py
- README.md
- types.py
- utils.py
- __init__.py
- actor_core.py
- actors.py
- actors_test.py
- builders.py
- normalization.py
- __init__.py
- learning.py
- README.md
- __init__.py
- discrete_learning.py
- discrete_learning_test.py
- README.md
- __init__.py
- recurrent_learning.py
- __init__.py
- agent.py
- agent_distributed.py
- agent_distributed_test.py
- agent_test.py
- learning.py
- networks.py
- README.md
- __init__.py
- agent.py
- agent_distributed.py
- agent_distributed_test.py
- agent_test.py
- learning.py
- README.md
- __init__.py
- agent.py
- agent_distributed.py
- agent_distributed_test.py
- agent_test.py
- learning.py
- README.md
- __init__.py
- agent.py
- agent_test.py
- bsuite_demonstrations.py
- README.md
- __init__.py
- agent.py
- agent_distributed.py
- agent_distributed_test.py
- agent_test.py
- learning.py
- README.md
- __init__.py
- acting.py
- agent.py
- agent_distributed.py
- agent_distributed_test.py
- agent_test.py
- learning.py
- README.md
- __init__.py
- learning.py
- learning_test.py
- README.md
- __init__.py
- base.py
- mlp.py
- simulator.py
- simulator_test.py
- __init__.py
- acting.py
- agent.py
- agent_distributed.py
- agent_test.py
- learning.py
- README.md
- search.py
- search_test.py
- types.py
- __init__.py
- agent_distributed.py
- learning.py
- networks.py
- README.md
- __init__.py
- agent.py
- agent_distributed.py
- agent_distributed_test.py
- agent_test.py
- learning.py
- README.md
- __init__.py
- agent.py
- agent_distributed.py
- agent_distributed_test.py
- agent_test.py
- learning.py
- README.md
- __init__.py
- agent.py
- agent_distributed.py
- agent_distributed_test.py
- agent_test.py
- learning.py
- README.md
- __init__.py
- agent.py
- agent_test.py
- README.md
- __init__.py
- acting.py
- agent.py
- agent_distributed.py
- agent_distributed_test.py
- agent_test.py
- learning.py
- networks.py
- README.md
- utils.py
- __init__.py
- actors.py
- actors_test.py
- __init__.py
- agent.py
- replay.py
- __init__.py
- image_augmentation.py
- numpy_iterator.py
- numpy_iterator_test.py
- reverb.py
- reverb_benchmark.py
- tfds.py
- __init__.py
- open_spiel_environment_loop.py
- open_spiel_environment_loop_test.py
- __init__.py
- config.py
- make_distributed_experiment.py
- make_distributed_offline_experiment.py
- run_experiment.py
- run_experiment_test.py
- run_offline_experiment.py
- run_offline_experiment_test.py
- test_utils.py
- __init__.py
- impala.py
- impala_test.py
- mpo.py
- wpo.py
- __init__.py
- atari.py
- base.py
- continuous.py
- distributional.py
- duelling.py
- embedding.py
- multiplexers.py
- policy_value.py
- rescaling.py
- resnet.py
- __init__.py
- imitation_learning_types.py
- inference_server.py
- observation_stacking.py
- running_statistics.py
- running_statistics_test.py
- savers.py
- savers_test.py
- snapshotter.py
- snapshotter_test.py
- types.py
- utils.py
- utils_test.py
- variable_utils.py
- variable_utils_test.py
- __init__.py
- types.py
- utils.py
- utils_test.py
- __init__.py
- fakes.py
- multiagent_fakes.py
- test_utils.py
- __init__.py
- distributional.py
- distributional_test.py
- dpg.py
- huber.py
- mompo.py
- mpo.py
- quantile.py
- r2d2.py
- __init__.py
- atari.py
- base.py
- continuous.py
- discrete.py
- distributional.py
- distributional_test.py
- distributions.py
- distributions_test.py
- duelling.py
- embedding.py
- legal_actions.py
- masked_epsilon_greedy.py
- multihead.py
- multiplexers.py
- noise.py
- policy_value.py
- quantile.py
- recurrence.py
- recurrence_test.py
- rescaling.py
- stochastic.py
- vision.py
- __init__.py
- savers.py
- savers_test.py
- utils.py
- utils_test.py
- variable_utils.py
- variable_utils_test.py
- __init__.py
- aggregators.py
- asynchronous.py
- auto_close.py
- base.py
- base_test.py
- constant.py
- csv.py
- csv_test.py
- dataframe.py
- default.py
- filters.py
- filters_test.py
- flatten.py
- image.py
- image_test.py
- terminal.py
- terminal_test.py
- tf_summary.py
- timestamp.py
- __init__.py
- action_metrics.py
- action_metrics_test.py
- action_norm.py
- action_norm_test.py
- base.py
- env_info.py
- env_info_test.py
- measurement_metrics.py
- measurement_metrics_test.py
- __init__.py
- async_utils.py
- counting.py
- counting_test.py
- experiment_utils.py
- frozen_learner.py
- frozen_learner_test.py
- iterator_utils.py
- iterator_utils_test.py
- lp_utils.py
- lp_utils_test.py
- metrics.py
- paths.py
- paths_test.py
- reverb_utils.py
- reverb_utils_test.py
- signals.py
- tree_utils.py
- tree_utils_test.py
- __init__.py
- action_repeat.py
- atari_wrapper.py
- atari_wrapper_dopamine.py
- atari_wrapper_test.py
- base.py
- base_test.py
- canonical_spec.py
- concatenate_observations.py
- delayed_reward.py
- delayed_reward_test.py
- expand_scalar_observation_shapes.py
- frame_stacking.py
- frame_stacking_test.py
- gym_wrapper.py
- gym_wrapper_test.py
- mujoco.py
- multiagent_dict_key_wrapper.py
- multigrid_wrapper.py
- noop_starts.py
- noop_starts_test.py
- observation_action_reward.py
- open_spiel_wrapper.py
- open_spiel_wrapper_test.py
- single_precision.py
- single_precision_test.py
- step_limit.py
- step_limit_test.py
- video.py
- __init__.py
- _metadata.py
- core.py
- core_test.py
- environment_loop.py
- environment_loop_test.py
- specs.py
- types.py
- custom.css
- acme-notext.png
- acme.png
- configure-and-run-experiments.png
- actor_loop.png
- agent_loop.png
- batch_loop.png
- distributed_loop.png
- environment_loop.png
- jax-small.png
- tf-small.png
- agents.md
- components.md
- overview.md
- conf.py
- faq.md
- index.rst
- requirements.txt
- helpers.py
- README.md
- run_bc.py
- run_gail.py
- run_iqlearn.py
- run_pwil.py
- run_sqil.py
- README.md
- helpers.py
- README.md
- run_d4pg.py
- run_dmpo.py
- run_mogmpo.py
- run_mpo.py
- run_ppo.py
- run_sac.py
- run_td3.py
- run_wpo.py
- helpers.py
- README.md
- run_dqn.py
- run_impala.py
- run_mdqn.py
- run_muzero.py
- run_qr_dqn.py
- run_r2d2.py
- README.md
- README.md
- run_dqn.py
- run_impala.py
- run_mcts.py
- helpers.py
- run_multigrid.py
- bc_utils.py
- run_bc.py
- run_bc_jax.py
- run_bcq.py
- run_cql_jax.py
- run_crr_jax.py
- run_dqfd.py
- run_mbop_jax.py
- run_offline_td3_jax.py
- run_dqn.py
- helpers.py
- lp_d4pg.py
- lp_ddpg.py
- lp_dmpo.py
- lp_dmpo_pixels.py
- lp_dmpo_pixels_drqv2.py
- lp_mpo.py
- quickstart.ipynb
- README.md
- tutorial.ipynb
- .gitignore
- .pylintrc
- .readthedocs.yaml
- CONTRIBUTING.md
- LICENSE
- MANIFEST.in
- README.md
- setup.py
- test.sh
# Installation Guide
1. Get the code
git clone https://github.com/google-deepmind/acme
Downloads the entire project code from GitHub to your computer.
cd acme
Moves into the project folder you just downloaded.
2. Official Install Script
Easy RecommendedPrerequisites
- Python 3 Python is required to use pip.
pip install --upgrade pip setuptools wheel
Installs the package published on PyPI directly β no need to clone the source.
pip install dm-acme[jax,tf]
Installs the package published on PyPI directly β no need to clone the source.
pip install dm-acme[envs]
Installs the package published on PyPI directly β no need to clone the source.
pip install .[jax,tf,testing,envs]
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. Python
EasyPrerequisites
python3 -m venv acme
Runs the Python script (or module).
pip install --upgrade pip setuptools wheel
Installs the package published on PyPI directly β no need to clone the source.
pip install dm-acme[jax,tf]
Installs the package published on PyPI directly β no need to clone the source.
pip install dm-acme[envs]
Installs the package published on PyPI directly β no need to clone the source.
pip install .[jax,tf,testing,envs]
Installs the package published on PyPI directly β no need to clone the source.
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)