arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2102.00966cs.LGcs.AI
收藏

基于分布式蒙特卡罗树搜索的风险意识多目标决策

Risk Aware and Multi-Objective Decision Making with Distributional Monte Carlo Tree Search

National University of Ireland Galway(爱尔兰国立高威大学)

Conor F. Hayes, Mathieu Reymond, Diederik M. Roijers, Enda Howley, Patrick Mannion

摘要:

在许多风险感知和多目标强化学习设置中,用户的效用来自策略的单次执行。在这种情况下,基于平均未来回报率的决策是不合适的。例如,在医疗环境中,患者可能只有一次机会治疗他们的疾病。在做决定时,仅仅是预期回报--在强化学习中被称为价值--不能解释一个决定可能产生的负面或正面结果的潜在范围。我们的关键见解是,我们应该使用不同的分布在预期的未来回报,以代表关键信息,代理人需要在决策时。在本文中,我们提出了分布式蒙特卡罗树搜索,学习后验分布的算法,从个人的政策执行可达到的不同的可能回报的效用,从而在风险意识和多目标设置良好的政策。此外,我们的算法优于国家的最先进的多目标强化学习的预期效用的回报。

英文摘要:

In many risk-aware and multi-objective reinforcement learning settings, the utility of the user is derived from the single execution of a policy. In these settings, making decisions based on the average future returns is not suitable. For example, in a medical setting a patient may only have one opportunity to treat their illness. When making a decision, just the expected return -- known in reinforcement learning as the value -- cannot account for the potential range of adverse or positive outcomes a decision may have. Our key insight is that we should use the distribution over expected future returns differently to represent the critical information that the agent requires at decision time. In this paper, we propose Distributional Monte Carlo Tree Search, an algorithm that learns a posterior distribution over the utility of the different possible returns attainable from individual policy executions, resulting in good policies for both risk-aware and multi-objective settings. Moreover, our algorithm outperforms the state-of-the-art in multi-objective reinforcement learning for the expected utility of the returns.

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。

↑