Peter Gehler

The Role of Pretrained Representations for the OOD Generalization of Reinforcement Learning Agents

2021 · arXiv (Cornell University)

Building sample-efficient agents that generalize out-of-distribution (OOD) in real-world settings remains a fundamental unsolved problem on the path towards achieving higher-level cognition. One particularly promising approach is to begin with low-dimensional, pretrained representations of our …