arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1805.09045cs.LGcs.AIstat.ML
收藏

当简单探索是样本有效的:确定随机探索产生PAC RL算法的充分条件

When Simple Exploration is Sample Efficient: Identifying Sufficient Conditions for Random Exploration to Yield PAC RL Algorithms

Stanford University(斯坦福大学)

Yao Liu, Emma Brunskill

摘要:

有效探索是强化学习(RL)算法面临的关键挑战之一。大多数传统的样本效率界限需要战略探索。最近,许多深度强化学习算法采用简单的启发式探索策略,几乎没有正式的保证,在许多领域取得了令人惊讶的成功。这些结果提出了一个重要的问题,了解这些探索策略,如$e$贪婪,以及了解什么特点的困难,探索MDP。在这项工作中,我们提出了特定问题的样本复杂性界的$Q$学习随机游走探索依赖于几个结构属性。我们还将我们的理论结果与一些经验基准域相关联,以说明我们的界是否在这些域中给出多项式样本复杂度,以及这与经验性能的关系。

英文摘要:

Efficient exploration is one of the key challenges for reinforcement learning (RL) algorithms. Most traditional sample efficiency bounds require strategic exploration. Recently many deep RL algorithms with simple heuristic exploration strategies that have few formal guarantees, achieve surprising success in many domains. These results pose an important question about understanding these exploration strategies such as $e$-greedy, as well as understanding what characterize the difficulty of exploration in MDPs. In this work we propose problem specific sample complexity bounds of $Q$ learning with random walk exploration that rely on several structural properties. We also link our theoretical results to some empirical benchmark domains, to illustrate if our bound gives polynomial sample complexity in these domains and how that is related with the empirical performance.

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。

↑