Natural Policy Gradient and Actor Critic Methods for Constrained Multi-Task Reinforcement Learning

arXiv:2405.02456v1 Announce Type: cross
Abstract: Multi-task reinforcement learning (RL) aims to find a single policy that effectively solves multiple tasks at the same time. This paper presents a constrained formulation for multi-task RL where the goal is to maximize the average performance of the policy across tasks subject to bounds on the performance in each task. We consider solving this problem both in the centralized setting, where information for all tasks is accessible to a single server, and in the …

abstract actor arxiv cs.lg gradient math.oc multiple natural paper performance policy reinforcement reinforcement learning tasks type