Finite-Time Convergence and Sample Complexity of Actor-Critic Multi-Objective Reinforcement Learning

arXiv:2405.03082v1 Announce Type: new
Abstract: Reinforcement learning with multiple, potentially conflicting objectives is pervasive in real-world applications, while this problem remains theoretically under-explored. This paper tackles the multi-objective reinforcement learning (MORL) problem and introduces an innovative actor-critic algorithm named MOAC which finds a policy by iteratively making trade-offs among conflicting reward signals. Notably, we provide the first analysis of finite-time Pareto-stationary convergence and corresponding sample complexity in both discounted and average reward settings. Our approach has two salient features: (a) …

abstract actor actor-critic algorithm applications arxiv complexity convergence cs.lg making multi-objective multiple paper policy reinforcement reinforcement learning sample trade type while world