改进了基于目标的强化学习中的经验回放方法，提升算法效率。
Maximum Entropy Hindsight Experience Replay
- 通过熵最大化策略，智能选择性地应用经验回放
- 在捕食者-猎物环境中，显著加速PPO算法收敛
- 适合研究目标导向强化学习的算法优化
Hindsight Experience Replay（HER）被广泛用于加速基于目标的强化学习（RL）。尽管HER通常应用于离线策略算法，我们此前已证明其也可加速在线策略算法（如近端策略优化，PPO）在基于目标的捕食者-猎物环境中的表现。本文进一步改进了PPO-HER算法，提出一种基于熵最大化的原则性选择机制，仅在有利条件下应用HER，从而提升训练效率与稳定性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。