When Data Geometry Meets Deep Function: Generalizing Offline Reinforcement Learning

Understand

In offline reinforcement learning (RL), one detrimental issue to policy learning is the error accumulation of deep Q function in out-of-distribution (OOD) areas.

• Unfortunately, existing offline RL methods are often over-conservative, inevitably hurting generalization performance outside data distribution.
• In our study, one interesting observation is that deep Q functions approximate well inside the convex hull of training data.
• Inspired by this, we propose a new method, DOGE (Distance-sensitive Offline RL with better GEneralization).