keiohta/tf2rl
A TensorFlow 2.x deep reinforcement learning library implementing on-policy and off-policy RL algorithms.
Not currently ranked — collecting fresh signals.
star history
TF2RL provides implementations of deep reinforcement learning algorithms including policy gradient methods (VPG, PPO), value-based methods (DQN, DDQN, Prioritized DQN, Dueling DQN, Distributional DQN, Noisy DQN), and actor-critic methods (DDPG, TD3, SAC). It supports both discrete and continuous action spaces and includes features like GAE for advantage estimation and Ape-X for distributed training.
Frequently asked
- What is keiohta/tf2rl?
- A TensorFlow 2.x deep reinforcement learning library implementing on-policy and off-policy RL algorithms.
- Is tf2rl open source?
- Yes — keiohta/tf2rl is open source, released under the MIT license.
- What language is tf2rl written in?
- keiohta/tf2rl is primarily written in Python.
- How popular is tf2rl?
- keiohta/tf2rl has 473 stars on GitHub.
- Where can I find tf2rl?
- keiohta/tf2rl is on GitHub at https://github.com/keiohta/tf2rl.