OpenAI Baselines

E17813

reinforcement learning toolkit software library

OpenAI Baselines is a collection of high-quality reference implementations of reinforcement learning algorithms released by OpenAI for research and benchmarking.

Try in SPARQL Jump to: Surface forms Statements Referenced by

All labels observed (2)

Label	Occurrences
OpenAI Baselines canonical	7
Stable Baselines	1

Statements (49)

Predicate	Object
instanceOf	reinforcement learning toolkit ⓘ software library ⓘ
category	open-source software ⓘ
compatibleWith	OpenAI Gym ⓘ
dependsOn	TensorFlow ⓘ
developer	OpenAI ⓘ
feature	common interfaces across algorithms ⓘ example training scripts ⓘ logging utilities ⓘ support for multiple environments ⓘ tested implementations ⓘ
genre	machine learning software ⓘ reinforcement learning ⓘ
goal	facilitate reproducible reinforcement learning research ⓘ provide high-quality reference implementations of RL algorithms ⓘ
implementsAlgorithm	A2C ⓘ A3C ⓘ ACKTR ⓘ DDPG ⓘ Atari deep Q-network ⓘ surface form: DQN DDPG ⓘ surface form: Deep Deterministic Policy Gradient Atari deep Q-network ⓘ surface form: Deep Q-Network Double DQN ⓘ Dueling DQN ⓘ GAIL ⓘ Her ⓘ surface form: HER Hindsight Experience Replay ⓘ PPO ⓘ PPO2 ⓘ Prioritized Experience Replay DQN ⓘ TRPO ⓘ
inspired	Stable Baselines ⓘ
license	MIT License ⓘ
maintainer	OpenAI ⓘ surface form: OpenAI (historical)
programmingLanguage	Python ⓘ
provides	reference implementations of reinforcement learning algorithms ⓘ
relatedTo	Stable Baselines ⓘ
repositoryPlatform	GitHub ⓘ
status	open source ⓘ
supports	actor-critic methods ⓘ policy gradient methods ⓘ value-based methods ⓘ
targetAudience	benchmark authors ⓘ machine learning researchers ⓘ reinforcement learning practitioners ⓘ
useCase	algorithm comparison ⓘ benchmarking ⓘ research ⓘ
writtenIn	Python ⓘ

Referenced by (8)

Full triples — surface form annotated when it differs from this entity's canonical label.

OpenAI → developed → OpenAI Baselines ⓘ

OpenAI Gym → influenced → OpenAI Baselines ⓘ

this entity surface form: Stable Baselines

OpenAI Gym → supports → OpenAI Baselines ⓘ

Stable Baselines → basedOn → OpenAI Baselines ⓘ

Stable Baselines → relatedTo → OpenAI Baselines ⓘ

A2C → implementedIn → OpenAI Baselines ⓘ

Hindsight Experience Replay → implementedIn → OpenAI Baselines ⓘ

Generalized Advantage Estimation → implementedIn → OpenAI Baselines ⓘ