ShangtongZhang/DeepRL
A PyTorch library implementing modular deep reinforcement learning algorithms for training agents in Atari and MuJoCo environments.
Not currently ranked — collecting fresh signals.
star history
This repository provides clean, modularized implementations of popular deep RL algorithms including DQN variants, policy gradient methods (A2C, PPO), off-policy methods (DDPG, TD3), and the Option-Critic architecture. It supports training agents in both Atari games and continuous control tasks (MuJoCo). The library uses asynchronous actors for data generation and asynchronous replay buffers for GPU utilization.
Frequently asked
- What is ShangtongZhang/DeepRL?
- A PyTorch library implementing modular deep reinforcement learning algorithms for training agents in Atari and MuJoCo environments.
- Is DeepRL open source?
- Yes — ShangtongZhang/DeepRL is open source, released under the MIT license.
- What language is DeepRL written in?
- ShangtongZhang/DeepRL is primarily written in Python.
- How popular is DeepRL?
- ShangtongZhang/DeepRL has 3.4k stars on GitHub.
- Where can I find DeepRL?
- ShangtongZhang/DeepRL is on GitHub at https://github.com/ShangtongZhang/DeepRL.