Flow Policy Gradients for Robot Control
This work addresses the problem of training expressive robot control policies for researchers and practitioners, representing an incremental improvement over existing methods.
The paper tackles the limitation of likelihood-based policy gradient methods in robot control by applying flow matching policy gradients to train more expressive policies, achieving success in legged locomotion, humanoid motion tracking, manipulation tasks, and robust sim-to-real transfer on two humanoid robots.
Likelihood-based policy gradient methods are the dominant approach for training robot control policies from rewards. These methods rely on differentiable action likelihoods, which constrain policy outputs to simple distributions like Gaussians. In this work, we show how flow matching policy gradients -- a recent framework that bypasses likelihood computation -- can be made effective for training and fine-tuning more expressive policies in challenging robot control settings. We introduce an improved objective that enables success in legged locomotion, humanoid motion tracking, and manipulation tasks, as well as robust sim-to-real transfer on two humanoid robots. We then present ablations and analysis on training dynamics. Results show how policies can exploit the flow representation for exploration when training from scratch, as well as improved fine-tuning robustness over baselines.