takuseno/d3rlpy
An offline deep reinforcement learning library for training agents using pre-collected datasets.

Velocity · 7d
+0.8
★ / day
Trend
→steady
star history
d3rlpy is a Python library for deep reinforcement learning that supports both offline and online training. It provides implementations of state-of-the-art offline RL algorithms for scenarios where online interaction is not feasible, such as robotics and medical applications. The library offers an intuitive API and is built on PyTorch.