Zero-Sum Positional Differential Games as a Framework for Robust Reinforcement Learning: Deep Q-Learning Approach

arXiv:2405.02044v1 Announce Type: new
Abstract: Robust Reinforcement Learning (RRL) is a promising Reinforcement Learning (RL) paradigm aimed at training robust to uncertainty or disturbances models, making them more efficient for real-world applications. Following this paradigm, uncertainty or disturbances are interpreted as actions of a second adversarial agent, and thus, the problem is reduced to seeking the agents' policies robust to any opponent's actions. This paper is the first to propose considering the RRL problems within the positional differential game theory, …

abstract adversarial applications arxiv cs.ai cs.gt cs.lg cs.sy differential eess.sy framework games interpreted making math.oc paradigm q-learning reinforcement reinforcement learning robust sum them training type uncertainty world