Amy Zhang

Regularized Latent Dynamics Prediction is a Strong Baseline For Behavioral Foundation Models

Reinforcement Learning via Value Gradient Flow

Hierarchical Entity-centric Reinforcement Learning with Factored Subgoal Diffusion

Multi-agent Coordination via Flow Matching

Reevaluating Policy Gradient Methods for Imperfect-Information Games

Self-Refining Vision Language Model for Robotic Failure Detection and Reasoning

A Unifying Perspective on Unsupervised Reinforcement Learning Algorithms

Learning to Interact in World Latent for Team Coordination

TRAM: Test-time Risk Adaptation with Mixture of Agents

CARE-RFT: Confidence-Anchored Reinforcement Finetuning for Reliable Reasoning in Large Language Models

Exploration for Deployment-Efficient Reinforcement Learning Agents

FLAM: Scaling Latent Action World Models with Factorization

MaestroMotif: Skill Design from Artificial Intelligence Feedback

Towards General-Purpose Model-Free Reinforcement Learning

Information-Theoretic Reward Decomposition for Generalizable RLHF

RLZero: Direct Policy Inference from Language Without In-Domain Supervision

ExPO: Unlocking Hard Reasoning with Self-Explanation-Guided Reinforcement Learning

Uni-RL: Unifying Online and Offline RL via Implicit Value Regularization

Proto Successor Measure: Representing the space of all possible solutions of Reinforcement Learning

Null Counterfactual Factor Interactions for Goal-Conditioned Reinforcement Learning

Learning a Fast Mixing Exogenous Block MDP using a Single Trajectory

EC-Diffuser: Multi-Object Manipulation via Entity-Centric Behavior Generation

Proto Successor Measure: Representing the Behavior Space of an RL Agent

An Optimal Discriminator Weighted Imitation Perspective for Reinforcement Learning

Online Intrinsic Rewards for Decision Making Agents from Large Language Model Feedback

Augmented Conditioning is Enough for Effective Training Image Generation