Simon S. Du

Is Long Horizon Reinforcement Learning More Difficult Than Short Horizon Reinforcement Learning?

2020 · arXiv (Cornell University)

Learning to plan for long horizons is a central challenge in episodic reinforcement learning problems. A fundamental question is to understand how the difficulty of the problem scales as the horizon increases. Here the natural …

Free from Bellman Completeness: Trajectory Stitching via Model-based Return-conditioned Supervised Learning

2023 · arXiv (Cornell University)

Off-policy dynamic programming (DP) techniques such as $Q$-learning have proven to be important in sequential decision-making problems. In the presence of function approximation, however, these techniques often diverge due to the absence of Bellman completeness …

Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination

2025 · arXiv (Cornell University)

Zero-shot coordination (ZSC), the ability to adapt to a new partner in a cooperative task, is a critical component of human-compatible AI. While prior work has focused on training agents to cooperate on a single …