TF-Agents

E97077

open-source project reinforcement learning framework software library

TF-Agents is an open-source library built on TensorFlow that provides modular components and tools for developing, training, and evaluating reinforcement learning algorithms.

Statements (49)

Predicate	Object
instanceOf	open-source project → reinforcement learning framework → software library →
basedOn	TensorFlow →
designedFor	production reinforcement learning systems → research in reinforcement learning →
developedBy	Google → Google Brain team →
hasComponent	agents → bandits library → drivers → environments → metrics → networks → policies → replay buffers →
hasFeature	data collection drivers → distributional RL support → experience replay → multi-armed bandits support →
hostedOn	GitHub →
isOpenSource	true →
license	Apache License 2.0 →
programmingLanguage	Python →
provides	documentation → example notebooks → modular components → tools for developing reinforcement learning algorithms → tools for evaluating reinforcement learning algorithms → tools for training reinforcement learning algorithms →
supports	TensorFlow 2 → continuous action spaces → discrete action spaces → eager execution → off-policy algorithms → on-policy algorithms → reinforcement learning → tf.function graphs →
supportsAlgorithmFamily	DDPG → DQN → PPO → REINFORCE → SAC → TD3 → actor-critic methods → policy gradient methods →
supportsEnvironment	Atari environments → MuJoCo environments → OpenAI Gym →

Referenced by (1)

Subject (surface form when different)	Predicate
TensorFlow →	hasComponent