最大熵后见之明经验回放
Maximum Entropy Hindsight Experience Replay
AI总结:
本研究针对基于目标的强化学习场景,提出通过有原则地选择性应用HER的方式,改进此前适配同策略PPO算法的PPO-HER方法,进一步提升后见之明经验回放的效果。
摘要:
后见之明经验回放(HER)是加速基于目标的强化学习(RL)的知名方法。尽管HER通常应用于离策略RL算法,我们此前已证明,在基于目标的捕食者-猎物环境中,HER也能加速近端策略优化(PPO)这类同策略算法。本文中,我们证明可通过有原则地选择性应用HER,改进此前的PPO-HER算法。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。