Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning (opens in new tab)  🎯Reinforcement Learning  Content type: Academic

Expressive continuous control policies, such as diffusion and flow models, form the backbone of recent advances in scaling imitation learning for simulated and real robot control. While they are known to scale stably in the supervised imitation learning setting, incorporating them into reinforcement learning (RL) pipelines for policy improvement has proven more difficult. It often requires specialized training objectives or backpropagating thr...