Safe Reinforcement Learning with Probabilistic Control Barrier Functions for Ramp Merging

no code implementations • 1 Dec 2022 • Soumith Udatha, Yiwei Lyu, John Dolan

We use probabilistic control barrier functions as an estimate of the model uncertainty.

Autonomous Driving Imitation Learning +3

Imitating Past Successes can be Very Suboptimal

no code implementations • 7 Jun 2022 • Benjamin Eysenbach, Soumith Udatha, Sergey Levine, Ruslan Salakhutdinov

Prior work has proposed a simple strategy for reinforcement learning (RL): label experience with the outcomes achieved in that experience, and then imitate the relabeled experience.

Imitation Learning Reinforcement Learning (RL)