TianhongDai/hindsight-experience-replay
PyTorch implementation of the Hindsight Experience Replay reinforcement learning algorithm for training agents on robotic manipulation tasks.
Not currently ranked — collecting fresh signals.
star history
This repository implements the HER algorithm in PyTorch to train DDPG agents on OpenAI Gym’s Fetch robotic manipulation environments. The implementation supports multi-process training via MPI and includes pre-trained models for FetchReach, FetchPush, FetchPickAndPlace, and FetchSlide tasks. It builds on the OpenAI Baselines codebase and targets robotics research applications.
Frequently asked
- What is TianhongDai/hindsight-experience-replay?
- PyTorch implementation of the Hindsight Experience Replay reinforcement learning algorithm for training agents on robotic manipulation tasks.
- Is hindsight-experience-replay open source?
- Yes — TianhongDai/hindsight-experience-replay is open source, released under the MIT license.
- What language is hindsight-experience-replay written in?
- TianhongDai/hindsight-experience-replay is primarily written in Python.
- How popular is hindsight-experience-replay?
- TianhongDai/hindsight-experience-replay has 451 stars on GitHub.
- Where can I find hindsight-experience-replay?
- TianhongDai/hindsight-experience-replay is on GitHub at https://github.com/TianhongDai/hindsight-experience-replay.