A discriminator-free occupancy matching approach for performant offline goal-conditioned reinforcement learning.

We propose Constrastive Preference Learning, a new supervised algorithm for learning optimal policies from regret-based preferences in general MDPs.

A unification of RL and IL methods through the lens of duality that allows us to propose new methods for discriminator-free imitation learning and stable offline reinforcement learning.

A unifying framework for learning from demonstrations and preferences. We develop methods to solve previously unsolvable tasks in the Learning from Observation (LfO) setting.

Improving RL with lookahead: LOOP is an efficient framework for RL to learn with a policy that finds the best action sequence using imaginary rollouts with a learned model. This allows LOOP to potentially reduce dependence on value function errors. LOOP achieves strong performance across a range of tasks and problem settings.

Combining DreamBooth (personalized text-to-image) and DreamFusion (text-to-3D) yields high-quality, subject-specific 3D assets with text-driven modifications

LBPO is a performant model-free safe RL method that leverages lyapunov constraints as barriers to guarantee safety. Our method shows state-of-the-art safety performance on OpenAI safety gym.

Want to get rid on alternating min-max optimization in IRL methods? Check out our method that differentiates through the max-entropy policy optimization to minimize divergence with the demonstrator. We learn transferrable reward function and achieve state of the art performance in imitation learning.

Robust lane detection by fusing multiple features.