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.
@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}
}