arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.06437cs.LGstat.ML
收藏

一种有效的强化学习样本收集策略

A Provably Efficient Sample Collection Strategy for Reinforcement Learning

Facebook AI Research(Facebook AI研究院);Inria Lille(里尔法国国家信息与自动化研究所);DeepMind

Jean Tarbouriech, Matteo Pirotta, Michal Valko, Alessandro Lazaric

摘要:

在线强化学习(RL)的挑战之一是智能体需要在环境探索和样本利用之间进行权衡,以优化其行为。无论我们是针对遗憾、样本复杂度、状态空间覆盖还是模型估计进行优化,我们都需要在探索与利用之间做出不同的权衡。在本文中,我们提出了一种解耦的方法来解决探索-利用问题,该方法由以下组成:1)一种“目标特定”算法,该算法(自适应地)规定在哪些状态下收集多少样本,就好像它可以访问生成模型(即,环境的模拟器); 2)负责尽可能快地生成规定样本的“客观不可知”样本收集探索策略。最近的方法探索在随机最短路径问题的基础上,我们首先提供了一个算法,作为输入的样本数$b(s,a)$需要在每个状态-动作对,需要$\tilde{O}(B D + D^{3/2} S^2 A)$时间步长收集$B=\sum_{s,a} b(s,a)$所需的样本,在任何未知的通信MDP与$S$状态,$A$行动和直径$D$。然后,我们展示了这种通用的探索算法如何与“特定目标”的策略配对,这些策略规定了样本要求,以解决各种设置-例如,模型估计,稀疏奖励发现,无目标无成本的探索在沟通MDP-我们获得改进或新的样本复杂性保证。

英文摘要:

One of the challenges in online reinforcement learning (RL) is that the agent needs to trade off the exploration of the environment and the exploitation of the samples to optimize its behavior. Whether we optimize for regret, sample complexity, state-space coverage or model estimation, we need to strike a different exploration-exploitation trade-off. In this paper, we propose to tackle the exploration-exploitation problem following a decoupled approach composed of: 1) An "objective-specific" algorithm that (adaptively) prescribes how many samples to collect at which states, as if it has access to a generative model (i.e., a simulator of the environment); 2) An "objective-agnostic" sample collection exploration strategy responsible for generating the prescribed samples as fast as possible. Building on recent methods for exploration in the stochastic shortest path problem, we first provide an algorithm that, given as input the number of samples $b(s,a)$ needed in each state-action pair, requires $\tilde{O}(B D + D^{3/2} S^2 A)$ time steps to collect the $B=\sum_{s,a} b(s,a)$ desired samples, in any unknown communicating MDP with $S$ states, $A$ actions and diameter $D$. Then we show how this general-purpose exploration algorithm can be paired with "objective-specific" strategies that prescribe the sample requirements to tackle a variety of settings -- e.g., model estimation, sparse reward discovery, goal-free cost-free exploration in communicating MDPs -- for which we obtain improved or novel sample complexity guarantees.

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。

↑