Statements (49)
Predicate | Object |
---|---|
gptkbp:instanceOf |
gptkb:software
|
gptkbp:basedOn |
gptkb:OpenAI_Baselines
|
gptkbp:compatibleWith |
gptkb:fitness_center
gptkb:PyTorch |
gptkbp:documentation |
https://stable-baselines3.readthedocs.io/
|
gptkbp:firstReleased |
2020
|
gptkbp:focusesOn |
gptkb:reinforcement_learning
|
gptkbp:hasFeature |
community support
modular design logging continuous integration monitoring policy evaluation callbacks extensive documentation unit tests custom policies easy-to-use API custom environment support examples and tutorials integration with TensorBoard model saving and loading multi-environment training support for continuous and discrete actions support for custom callbacks support for custom environments support for custom policies support for multiprocessing vectorized environments |
https://www.w3.org/2000/01/rdf-schema#label |
Stable Baselines3
|
gptkbp:implementedIn |
deep reinforcement learning algorithms
|
gptkbp:latestReleaseVersion |
2024-03-13
1.8.0 |
gptkbp:license |
gptkb:MIT_License
|
gptkbp:maintainedBy |
DLR-RM
|
gptkbp:programmingLanguage |
gptkb:Python
|
gptkbp:repository |
https://github.com/DLR-RM/stable-baselines3
|
gptkbp:supportsAlgorithm |
gptkb:A2C
gptkb:DDPG gptkb:DQN gptkb:TD3 gptkb:SAC PPO |
gptkbp:usedFor |
education
research benchmarking RL algorithms training reinforcement learning agents |
gptkbp:bfsParent |
gptkb:Stable_Baselines
|
gptkbp:bfsLayer |
6
|