2 papers
cs.LG2025
Long-Horizon Model-Based Offline Reinforcement Learning Without Explicit Conservatism
Tianwei Ni, Esther Derman, Vineet Jain +3
Popular offline reinforcement learning (RL) methods rely on explicit conservatism, penalizing out-of-dataset actions or restricting rollout horizons. We question the universality o…
cs.LG2025
Understanding Behavioral Metric Learning: A Large-Scale Study on Distracting Reinforcement Learning Environments
Ziyan Luo, Tianwei Ni, Pierre-Luc Bacon +2
A key approach to state abstraction is approximating behavioral metrics (notably, bisimulation metrics) in the observation space and embedding these learned distances in the repres…