Distributionally-Constrained Policy Optimization via Unbalanced Optimal Transport

Abstract

We consider constrained policy optimization in Reinforcement Learning, where the constraints are in form of marginals on state visitations and global action executions. Given these distributions, we formulate policy optimization as unbalanced optimal transport over the space of occupancy measures. We propose a general purpose RL objective based on Bregman divergence and optimize it using Dykstra's algorithm. The approach admits an actor-critic algorithm for when the state or action space is large, and only samples from the marginals are available. We discuss applications of our approach and provide demonstrations to show the effectiveness of our algorithm.

References in corpus (6)

• A unified view of entropy-regularized Markov decision processes
• AlgaeDICE: Policy Gradient from Arbitrary Experience
• Variational Policy Gradient Method for Reinforcement Learning with General Utilities
• Wasserstein Adversarial Imitation Learning
• Reinforcement Learning via Fenchel-Rockafellar Duality
• Cautious Reinforcement Learning via Distributional Risk in the Dual Domain