pfnet/pfrl
A PyTorch library implementing deep reinforcement learning algorithms including DQN, Rainbow, and other state-of-the-art methods.
Not currently ranked — collecting fresh signals.
star history
PFRL is a deep reinforcement learning library that provides implementations of various state-of-the-art RL algorithms using PyTorch. It supports discrete and continuous action spaces, recurrent models, batch training, and includes pretrained models. The library offers examples for Atari 2600 and OpenAI Gym environments, making it suitable for training agents in diverse RL scenarios.
Frequently asked
- What is pfnet/pfrl?
- A PyTorch library implementing deep reinforcement learning algorithms including DQN, Rainbow, and other state-of-the-art methods.
- Is pfrl open source?
- Yes — pfnet/pfrl is open source, released under the MIT license.
- What language is pfrl written in?
- pfnet/pfrl is primarily written in Python.
- How popular is pfrl?
- pfnet/pfrl has 1.3k stars on GitHub.
- Where can I find pfrl?
- pfnet/pfrl is on GitHub at https://github.com/pfnet/pfrl.