GenerativeRL
Python library for solving reinforcement learning (RL) problems using generative models (e.g. Diffusion Models).
File Explorer
Download Latest Version (.zip)- doc.yml
- release.yml
- unit_test.yml
- framework.png
- style.css
- logo.png
- layout.html
- index.rst
- index.rst
- index.rst
- index.rst
- index.rst
- index.rst
- index.rst
- index.rst
- index.rst
- index.rst
- index.rst
- evaluating_agents.rst
- index.rst
- installation.rst
- training_agents.rst
- training_generative_models.rst
- all.mk
- conf.py
- diagrams.mk
- graphviz.mk
- index.rst
- Makefile
- __init__.py
- base.py
- gm.py
- idql.py
- qgpo.py
- srpo.py
- __init__.py
- base.py
- gmpg.py
- gmpo.py
- idql.py
- qgpo.py
- srpo.py
- __init__.py
- d4rl.py
- gp.py
- minari_dataset.py
- qgpo.py
- function.py
- guided_bridge_conditional_flow_model.py
- schrodinger_bridge_conditional_flow_model.py
- __init__.py
- guided_conditional_flow_model.py
- independent_conditional_flow_model.py
- optimal_transport_conditional_flow_model.py
- __init__.py
- diffusion_model.py
- energy_conditional_diffusion_model.py
- guided_diffusion_model.py
- __init__.py
- discrete_flow_matching.py
- __init__.py
- data_prediction_function.py
- noise_function.py
- score_function.py
- velocity_function.py
- flow.py
- __init__.py
- diffusion_process.py
- intrinsic_model.py
- metric.py
- random_generator.py
- sro.py
- stochastic_process.py
- variational_autoencoder.py
- __init__.py
- fourier_neural_operator.py
- __init__.py
- dit.py
- maxvit.py
- uvit.py
- __init__.py
- unet_2D.py
- __init__.py
- activation.py
- encoders.py
- residual_network.py
- __init__.py
- dpm_solver.py
- ode_solver.py
- sde_solver.py
- __init__.py
- monte_carlo.py
- ode.py
- probability_path.py
- sde.py
- __init__.py
- base.py
- __init__.py
- buffer_by_torchrl.py
- __init__.py
- base.py
- dm_control_env_simulator.py
- gym_env_simulator.py
- __init__.py
- one_shot_value_function.py
- q_network.py
- value_network.py
- dynamic_model.py
- state_prior_dynamic_model.py
- __init__.py
- functions.py
- test_diffusion_model.py
- test_random_generator.py
- test_activation.py
- test_encoder.py
- test_buffer_by_torchrl.py
- test_model_utils.py
- test_plot.py
- __init__.py
- config.py
- huggingface.py
- log.py
- model_utils.py
- plot.py
- statistics.py
- __init__.py
- __init__.py
- dm_control_suit_cartpole_swing.py
- dm_control_suit_cheetah_run.py
- dm_control_suit_finger_turn_hard.py
- dm_control_suit_fish_swim.py
- dm_control_suit_humanoid_run.py
- dm_control_suit_manipulator_insert_ball.py
- dm_control_suit_manipulator_insert_peg.py
- dm_control_suit_rodent_gaps.py
- dm_control_suit_walker_stand.py
- dm_control_suit_walker_walk.py
- dmcontrol_suit_humanoid_run.py
- halfcheetah_medium.py
- halfcheetah_medium_expert.py
- halfcheetah_medium_replay.py
- hopper_medium.py
- hopper_medium_expert.py
- hopper_medium_replay.py
- walker2d_medium.py
- walker2d_medium_expert.py
- walker2d_medium_replay.py
- __init__.py
- halfcheetah_medium.py
- halfcheetah_medium_expert.py
- halfcheetah_medium_replay.py
- hopper_medium.py
- hopper_medium_expert.py
- hopper_medium_replay.py
- walker2d_medium.py
- walker2d_medium_expert.py
- walker2d_medium_replay.py
- __init__.py
- antmaze_large_diverse.py
- antmaze_large_play.py
- antmaze_medium_diverse.py
- antmaze_medium_play.py
- antmaze_umaze.py
- antmaze_umaze_diverse.py
- halfcheetah_medium.py
- halfcheetah_medium_expert.py
- halfcheetah_medium_replay.py
- hopper_medium.py
- hopper_medium_expert.py
- hopper_medium_replay.py
- walker2d_medium.py
- walker2d_medium_expert.py
- walker2d_medium_replay.py
- __init__.py
- antmaze_large_diverse.py
- antmaze_large_play.py
- antmaze_medium_diverse.py
- antmaze_medium_play.py
- antmaze_umaze.py
- antmaze_umaze_diverse.py
- dm_control_suit_cartpole_swing.py
- dm_control_suit_cheetah_run.py
- dm_control_suit_finger_turn_hard.py
- dm_control_suit_fish_swim.py
- dm_control_suit_humanoid_run.py
- dm_control_suit_manipulator_insert_ball.py
- dm_control_suit_manipulator_insert_peg.py
- dm_control_suit_walker_stand.py
- dm_control_suit_walker_walk.py
- halfcheetah_medium.py
- halfcheetah_medium_expert.py
- halfcheetah_medium_replay.py
- hopper_medium.py
- hopper_medium_expert.py
- hopper_medium_replay.py
- walker2d_medium.py
- walker2d_medium_expert.py
- walker2d_medium_replay.py
- __init__.py
- halfcheetah_medium.py
- halfcheetah_medium_expert.py
- halfcheetah_medium_replay.py
- hopper_medium.py
- hopper_medium_expert.py
- hopper_medium_replay.py
- walker2d_medium.py
- walker2d_medium_expert.py
- walker2d_medium_replay.py
- __init__.py
- halfcheetah_medium.py
- halfcheetah_medium_expert.py
- halfcheetah_medium_replay.py
- hopper_medium.py
- hopper_medium_expert.py
- hopper_medium_replay.py
- walker2d_medium.py
- walker2d_medium_expert.py
- walker2d_medium_replay.py
- dm_control_suit_cartpole_swingup.py
- dm_control_suit_cheetah_run.py
- dm_control_suit_finger_turn_hard.py
- dm_control_suit_fish_swim.py
- dm_control_suit_humanoid_run.py
- dm_control_suit_manipulator_insert_ball.py
- dm_control_suit_manipulator_insert_peg.py
- dm_control_suit_walker_stand.py
- dm_control_suit_walker_walk.py
- halfcheetah_medium.py
- halfcheetah_medium_expert.py
- halfcheetah_medium_replay.py
- hopper_medium.py
- hopper_medium_expert.py
- hopper_medium_replay.py
- walker2d_medium.py
- walker2d_medium_expert.py
- walker2d_medium_replay.py
- dm_control_suit_cartpole_swingup.py
- dm_control_suit_cheetah_run.py
- dm_control_suit_finger_turn_hard.py
- dm_control_suit_fish_swim.py
- dm_control_suit_manipulator_insert_ball.py
- dm_control_suit_manipulator_insert_peg.py
- dm_control_suit_walker_stand.py
- dm_control_suit_walker_walk.py
- halfcheetah_medium.py
- halfcheetah_medium_expert.py
- halfcheetah_medium_replay.py
- hopper_medium.py
- hopper_medium_expert.py
- hopper_medium_replay.py
- walker2d_medium.py
- walker2d_medium_expert.py
- walker2d_medium_replay.py
- generative_policy.png
- README.md
- README.zh.md
- __init__.py
- d4rl_halfcheetah_qgpo.py
- d4rl_walker2d_qgpo.py
- lunarlander_continuous_qgpo.py
- __init__.py
- d4rl_halfcheetah_qgpo.py
- d4rl_walker2d_qgpo.py
- lunarlander_continuous_qgpo.py
- swiss_roll_world_model.py
- swiss_roll_diffusion.py
- swiss_roll_discrete_flow_model.py
- swiss_roll_energy_condition.py
- swiss_roll_icfm.py
- swiss_roll_icfm_with_mask.py
- swiss_roll_otcfm.py
- swiss_roll_sf2m.py
- lunarlander_continuous_qgpo_huggingface_pull.py
- lunarlander_continuous_qgpo_huggingface_push.py
- modelcard_template.md
- swiss_roll_likelihood.py
- swiss_roll_dpmsolver.py
- swiss_roll_sdesolver.py
- customized_modules.py
- dict_tensor_ode.py
- README.md
- README.zh.md
- __init__.py
- base.py
- .gitignore
- .style.yapf
- CHANGELOG
- CONTRIBUTING.md
- LICENSE
- README.md
- README.zh.md
- requirements-doc.txt
- setup.py
# Installation Guide
1. Get the code
git clone https://github.com/opendilab/GenerativeRL
Downloads the entire project code from GitHub to your computer.
cd GenerativeRL
Moves into the project folder you just downloaded.
2. Official Install Script
Easy RecommendedPrerequisites
- Python 3 Python is required to use pip.
pip install GenerativeRL
Installs the package published on PyPI directly โ no need to clone the source.
pip install 'gym[box2d]==0.23.1'
Installs the package published on PyPI directly โ 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
pip install GenerativeRL
Installs the package published on PyPI directly โ no need to clone the source.
pip install -e .
Installs the Python libraries listed in requirements.txt (or similar).
pip install 'gym[box2d]==0.23.1'
Installs the package published on PyPI directly โ 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)