astooke/rlpyt
A PyTorch library implementing deep reinforcement learning algorithms for training agents.
Not currently ranked — collecting fresh signals.
star history
rlpyt provides modular, optimized implementations of common deep RL algorithms in PyTorch, supporting all three major families of model-free methods: policy gradient, deep Q-learning, and Q-function policy gradient. The library offers unified infrastructure for running experiments serially or in parallel, with optional multi-GPU optimization using PyTorch’s DistributedDataParallel. It supports CPU or GPU training, synchronous or asynchronous sampling, and full recurrent agent capabilities for small- to medium-scale research.
Frequently asked
- What is astooke/rlpyt?
- A PyTorch library implementing deep reinforcement learning algorithms for training agents.
- Is rlpyt open source?
- Yes — astooke/rlpyt is open source, released under the MIT license.
- What language is rlpyt written in?
- astooke/rlpyt is primarily written in Python.
- How popular is rlpyt?
- astooke/rlpyt has 2.3k stars on GitHub.
- Where can I find rlpyt?
- astooke/rlpyt is on GitHub at https://github.com/astooke/rlpyt.