Reinforcement Learning

We study the problem of action sampling and propose a method to incorporate equivariance properties to the action sampling procedure.

This work learns to navigate end-to-end with map input, aiming to generalize to novel map layouts in zero-shot.

We study whether Euclidean symmetry can help in reinforcement learning and planning, which models the geometric transformations between reference frames of robots.

We formulate how differentiable planning algorithms can exploit inherent symmetry in path planning problems, named SymPlan, and propose practical algorithms.

We study how implicit differentiation helps scale up and improve convergence of differentiable planning algorithms.

We formulate compositional generalization in object-oriented world modeling, and propose a soft and efficient mechanism for practice.

We learn latent representations enforced with known transformation laws (group action), and apply this idea on equivariant latent world modeling.

This work aims to improve the zero-shot generalization performance in map-based navigation on novel layouts.

We propose a parameterized action reinforcement learning algorithm to improve the performance of match plan generation in Bing search.