Score: 2

Wasserstein Policy Optimization

Published: May 1, 2025 | arXiv ID: 2505.00663v1

By: David Pfau , Ian Davies , Diana Borsa and more

BigTech Affiliations: Google

Potential Business Impact:

Teaches robots to move smoothly and learn faster.

Business Areas:
A/B Testing Data and Analytics

We introduce Wasserstein Policy Optimization (WPO), an actor-critic algorithm for reinforcement learning in continuous action spaces. WPO can be derived as an approximation to Wasserstein gradient flow over the space of all policies projected into a finite-dimensional parameter space (e.g., the weights of a neural network), leading to a simple and completely general closed-form update. The resulting algorithm combines many properties of deterministic and classic policy gradient methods. Like deterministic policy gradients, it exploits knowledge of the gradient of the action-value function with respect to the action. Like classic policy gradients, it can be applied to stochastic policies with arbitrary distributions over actions -- without using the reparameterization trick. We show results on the DeepMind Control Suite and a magnetic confinement fusion task which compare favorably with state-of-the-art continuous control methods.

Country of Origin
🇺🇸 United States

Repos / Data Links

Page Count
22 pages

Category
Computer Science:
Machine Learning (CS)