Anchor-Changing Regularized Natural Policy Gradient for Multi-Objective Reinforcement Learning

• URL: http://arxiv.org/abs/2206.05357v1
• Date: Fri, 10 Jun 2022 21:09:44 GMT
• Title: Anchor-Changing Regularized Natural Policy Gradient for Multi-Objective Reinforcement Learning
• Authors: Ruida Zhou, Tao Liu, Dileep Kalathil, P. R. Kumar, Chao Tian
• Abstract summary: We study policy optimization for Markov decision processes (MDPs) with multiple reward value functions. We propose an Anchor-changing Regularized Natural Policy Gradient framework, which can incorporate ideas from well-performing first-order methods.
• Score: 17.916366827429034
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study policy optimization for Markov decision processes (MDPs) with multiple reward value functions, which are to be jointly optimized according to given criteria such as proportional fairness (smooth concave scalarization), hard constraints (constrained MDP), and max-min trade-off. We propose an Anchor-changing Regularized Natural Policy Gradient (ARNPG) framework, which can systematically incorporate ideas from well-performing first-order methods into the design of policy optimization algorithms for multi-objective MDP problems. Theoretically, the designed algorithms based on the ARNPG framework achieve $\tilde{O}(1/T)$ global convergence with exact gradients. Empirically, the ARNPG-guided algorithms also demonstrate superior performance compared to some existing policy gradient-based approaches in both exact gradients and sample-based scenarios.

Related papers

Err

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.