Adaptive Neighborhood-Constrained Q Learning for Offline Reinforcement Learning
NeurIPSSpotlight2025
TL;DR
Offline reinforcement learning (RL) suffers from extrapolation errors induced by out-of-distribution (OOD) actions…
Opening excerpt from the authors’ abstract. source
Read the paper
Topics
offline reinforcement learning reinforcement learning
← All NeurIPS 2025 Spotlight papers · Browse the whole archive