Kavli Affiliate: Jia Liu | First 5 Authors: Tianchen Zhou, FNU Hairi, Haibo Yang, Jia Liu, Tian Tong | Summary: 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 […]
Continue.. Finite-Time Convergence and Sample Complexity of Actor-Critic Multi-Objective Reinforcement Learning