Shypd.aiThe largest open index of AI toolsDRLib is an open-source deep reinforcement learning library that integrates HER, PER, and D2SR for off-policy RL algorithms. It supports both TensorFlow and PyTorch for flexible implementation.
Trending
Also listed in
About
DRLib is a concise deep reinforcement learning library designed to integrate almost all off-policy RL algorithms with Hindsight Experience Replay (HER) and Prioritized Experience Replay (PER). Built upon OpenAI's spinningup, it offers implementations in both TensorFlow and PyTorch. The library simplifies the original spinningup code by removing multi-process and experimental grid wrappers for easier application and debugging. It also incorporates the D2SR method for efficient reward function design. DRLib is particularly well-suited for robotics-related tasks, providing encapsulated DDPG, TD3, and SAC algorithms with GPU support for PyTorch.
Capabilities
Pricing & Plans
Open Source
Free
FAQs
Trending
