Wasserstein Reinforcement Learning.
Year: 2019
Type: preprint
Abstract: We propose behavior-driven optimization via Wasserstein distances (WDs) toimprove several classes of state-of-the-art reinforcement learning (RL)
algorithms. We show that WD regularizers acting on appropriate policy
embeddings efficiently incorporate behavioral characteristics into policy
optimization. We demonstrate that they improve Evolution Strategy methods by
encouraging more efficient exploration, can be applied in imitation learning
and to speed up training of Trust Region Policy Optimization methods. Since the
exact computation of WDs is expensive, we develop approximate algorithms based
on the combination of different methods: dual formulation of the optimal
transport problem, alternating optimization and random feature maps, to
effectively replace exact WD computations in the RL tasks considered. We
provide theoretical analysis of our algorithms and exhaustive empirical
evaluation in a variety of RL settings.
Source: arXiv (Cornell University)
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2952653857