arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2204.09424cs.LGcs.AIcs.GT
收藏

SAAC:安全的强化学习作为演员-评论家的对抗游戏

SAAC: Safe Reinforcement Learning as an Adversarial Game of Actor-Critics

Stanford University(斯坦福大学);Univ. Lille(里尔大学);Inria(法国国家信息与自动化研究所);CNRS(法国国家科学研究中心);Centrale Lille(里尔中央理工学院)

Yannis Flet-Berliac, Debabrota Basu

摘要:

尽管强化学习(RL)对于不确定性下的顺序决策问题是有效的,但它仍然无法在风险或安全是约束性约束的现实世界系统中蓬勃发展。在本文中,我们制定了RL问题的安全约束作为一个非零和游戏。虽然部署了最大熵RL,但这种提法导致了一个安全的对抗引导的软演员-评论家框架,称为SAAC。在SAAC中,对手的目标是打破安全约束,而RL代理的目标是最大化受约束的价值函数给定对手的政策。对代理人的价值函数的安全约束只表现为代理人和对手的政策之间的排斥项。与以前的方法不同,SAAC可以解决不同的安全标准,如安全探索,均值-方差风险敏感性,CVaR的一致性风险敏感性。我们说明了这些限制的对手的设计。然后,在这些变化中的每一个,我们表明代理区分自己从对手的不安全的行动,除了学习解决任务。最后,对于具有挑战性的连续控制任务,我们证明了SAAC实现更快的收敛速度,更好的效率,更少的故障,以满足安全约束比风险厌恶的分布式RL和风险中性的软演员批评算法。

英文摘要:

Although Reinforcement Learning (RL) is effective for sequential decision-making problems under uncertainty, it still fails to thrive in real-world systems where risk or safety is a binding constraint. In this paper, we formulate the RL problem with safety constraints as a non-zero-sum game. While deployed with maximum entropy RL, this formulation leads to a safe adversarially guided soft actor-critic framework, called SAAC. In SAAC, the adversary aims to break the safety constraint while the RL agent aims to maximize the constrained value function given the adversary's policy. The safety constraint on the agent's value function manifests only as a repulsion term between the agent's and the adversary's policies. Unlike previous approaches, SAAC can address different safety criteria such as safe exploration, mean-variance risk sensitivity, and CVaR-like coherent risk sensitivity. We illustrate the design of the adversary for these constraints. Then, in each of these variations, we show the agent differentiates itself from the adversary's unsafe actions in addition to learning to solve the task. Finally, for challenging continuous control tasks, we demonstrate that SAAC achieves faster convergence, better efficiency, and fewer failures to satisfy the safety constraints than risk-averse distributional RL and risk-neutral soft actor-critic algorithms.

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。

↑