arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.05477cs.LGcs.AIcs.ROcs.SYeess.SYstat.ML
收藏

逆强化学习的最大似然约束推理

Maximum Likelihood Constraint Inference for Inverse Reinforcement Learning

University of California, Berkeley(加州大学伯克利分校)

Dexter R. R. Scobee, S. Shankar Sastry

摘要:

虽然逆强化学习(IRL)问题的大多数方法都集中在估计最能解释专家代理在控制任务上的策略或表现行为的奖励函数,但通常情况下,这种行为更简洁地表示为简单的奖励与一组硬约束的组合。在这种情况下,智能体试图最大化累积奖励,但要受到对其行为的这些给定约束。我们重新制定的马尔可夫决策过程(MDPs)的IRL的问题,这样,给定一个名义上的环境模型和名义上的奖励函数,我们试图估计状态,动作,并在环境中的功能约束,激励代理的行为。我们的方法是基于最大熵IRL框架,这使我们能够推理的可能性,一个专家代理的演示给我们的知识的MDP。使用我们的方法,我们可以推断哪些约束可以添加到MDP中,以最大限度地增加观察这些演示的可能性。我们提出了一种算法,迭代推断的最大似然约束,以最好地解释观察到的行为,我们评估其有效性,使用模拟的行为和记录的数据的人类导航周围的障碍。

英文摘要:

While most approaches to the problem of Inverse Reinforcement Learning (IRL) focus on estimating a reward function that best explains an expert agent's policy or demonstrated behavior on a control task, it is often the case that such behavior is more succinctly represented by a simple reward combined with a set of hard constraints. In this setting, the agent is attempting to maximize cumulative rewards subject to these given constraints on their behavior. We reformulate the problem of IRL on Markov Decision Processes (MDPs) such that, given a nominal model of the environment and a nominal reward function, we seek to estimate state, action, and feature constraints in the environment that motivate an agent's behavior. Our approach is based on the Maximum Entropy IRL framework, which allows us to reason about the likelihood of an expert agent's demonstrations given our knowledge of an MDP. Using our method, we can infer which constraints can be added to the MDP to most increase the likelihood of observing these demonstrations. We present an algorithm which iteratively infers the Maximum Likelihood Constraint to best explain observed behavior, and we evaluate its efficacy using both simulated behavior and recorded data of humans navigating around an obstacle.

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。

↑