English

Maximum Entropy Hindsight Experience Replay

Machine Learning 2024-11-01 v1

Abstract

Hindsight experience replay (HER) is well-known to accelerate goal-based reinforcement learning (RL). While HER is generally applied to off-policy RL algorithms, we previously showed that HER can also accelerate on-policy algorithms, such as proximal policy optimization (PPO), for goal-based Predator-Prey environments. Here, we show that we can improve the previous PPO-HER algorithm by selectively applying HER in a principled manner.

Keywords

Cite

@article{arxiv.2410.24016,
  title  = {Maximum Entropy Hindsight Experience Replay},
  author = {Douglas C. Crowder and Matthew L. Trappett and Darrien M. McKenzie and Frances S. Chance},
  journal= {arXiv preprint arXiv:2410.24016},
  year   = {2024}
}

Comments

11 pages, 11 Figures

R2 v1 2026-06-28T19:43:00.986Z