Peter Stone

A Unifying Perspective on Unsupervised Reinforcement Learning Algorithms

Adversarial Reinforcement Learning for Large Language Model Agent Safety

ROTATE: Regret-driven Open-ended Training for Ad Hoc Teamwork

FLAM: Scaling Latent Action World Models with Factorization

SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning

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

Hyperspherical Normalization for Scalable Deep Reinforcement Learning

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

Dyn-O: Building Structured World Models with Object-Centric Representations

Learning a Fast Mixing Exogenous Block MDP using a Single Trajectory

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

Longhorn: State Space Models are Amortized Online Learners

Influencing Humans to Conform to Preference Models for RLHF

Talking Vehicles: Cooperative Driving via Natural Language