Peter Stone

8

Papers

78

Total Citations

Papers (8)

Longhorn: State Space Models are Amortized Online Learners

Minimum Coverage Sets for Training Robust Ad Hoc Teamwork Agents

Learning Optimal Advantage from Preferences and Mistaking It for Reward

Building Minimal and Reusable Causal State Abstractions for Reinforcement Learning

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

NeurIPS 2025arXiv

Sample Efficient Myopic Exploration Through Multitask Reinforcement Learning with Diverse Tasks

Learning a Fast Mixing Exogenous Block MDP using a Single Trajectory

Argus: A Compact and Versatile Foundation Model for Vision