Reinforcement Learning

Equivariant Action Sampling for Reinforcement Learning and Planning

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

Learning to Navigate in Mazes with Novel Layouts Using Abstract Top-down Maps

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

Can Euclidean Symmetry Help in Reinforcement Learning and Planning?

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

Integrating Symmetry into Differentiable Planning with Steerable Convolutions

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

Scaling up and Stabilizing Differentiable Planning with Implicit Differentiation

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

Toward Compositional Generalization in Object‑Oriented World Modeling

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

Learning Symmetric Embeddings for Equivariant World Models

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

Model-based Navigation in Environments with Novel Layouts Using Abstract 2-D Maps

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

Match Plan Generation in Web Search with Parameterized Action Reinforcement Learning

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

InterFact: Towards Interactive Factorization of Actionable Entities

This work proposes a reinforcement learning framework for compositional object-oriented environments.