arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.12686cs.LGq-fin.RMstat.ML
收藏

风险敏感的强化学习:一种奖励不确定性的鞅方法

Risk-Sensitive Reinforcement Learning: a Martingale Approach to Reward Uncertainty

JP Morgan AI Research(摩根大通人工智能研究院)

Nelson Vadori, Sumitra Ganesh, Prashant Reddy, Manuela Veloso

摘要:

我们引入了一个新的框架来解释敏感性奖励的不确定性顺序决策问题。虽然到目前为止研究的马尔可夫决策过程的风险敏感配方集中在作为一个整体的累积奖励的分布,我们的目标是学习政策敏感的奖励的不确定性/随机性,这在某些情况下具有概念上更有意义的优势。为此,我们提出了一个新的分解的随机性包含在累积奖励的基础上的Doob分解的随机过程,并引入了一个新的概念工具-\textit{chaotic variation} -它可以被严格地解释为风险度量的鞅分量相关的累积奖励过程。我们在强化学习方面进行了创新,将这种新的风险敏感方法融入到无模型算法中,基于策略梯度和价值函数,并说明了其在网格世界和投资组合优化问题上的相关性。

英文摘要:

We introduce a novel framework to account for sensitivity to rewards uncertainty in sequential decision-making problems. While risk-sensitive formulations for Markov decision processes studied so far focus on the distribution of the cumulative reward as a whole, we aim at learning policies sensitive to the uncertain/stochastic nature of the rewards, which has the advantage of being conceptually more meaningful in some cases. To this end, we present a new decomposition of the randomness contained in the cumulative reward based on the Doob decomposition of a stochastic process, and introduce a new conceptual tool - the \textit{chaotic variation} - which can rigorously be interpreted as the risk measure of the martingale component associated to the cumulative reward process. We innovate on the reinforcement learning side by incorporating this new risk-sensitive approach into model-free algorithms, both policy gradient and value function based, and illustrate its relevance on grid world and portfolio optimization problems.

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。

↑