paper-with-me

홈 › Papers

Understanding What Affects the Generalization Gap in Visual Reinforcement Learning: Theory and Empirical Evidence

2024-02-05 · Jiafei Lyu, Le Wan, Xiu Li, Zongqing Lu

Recently, there are many efforts attempting to learn useful policies for continuous control in visual reinforcement learning (RL). In this scenario, it is important to learn a generalizable policy, as the testing environment may differ from the training environment, e.g., there exist distractors during deployment. Many practical algorithms are proposed to handle this problem. However, to the best of our knowledge, none of them provide a theoretical understanding of what affects the generalization gap and why their proposed methods work. In this paper, we bridge this issue by theoretically answering the key factors that contribute to the generalization gap when the testing environment has distractors. Our theories indicate that minimizing the representation distance between training and testing environments, which aligns with human intuition, is the most critical for the benefit of reducing the generalization gap. Our theoretical results are supported by the empirical evidence in the DMControl Generalization Benchmark (DMC-GB).

📄 PDF Abstract BibTeX arXiv:2402.02701

Code (0)

등록된 구현이 없습니다.

Tasks

continuous-controlContinuous ControlLearning TheoryReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

How Does RL Post-training Induce Skill Composition? A Case Study on Countdown

2025-12-01 · Simon Park, Simran Kaur, Sanjeev Arora arxiv

While reinforcement learning (RL) successfully enhances reasoning in large language models, its role in fostering compositional generalization (the ability to synthesize novel skills from known components) is often confl…

Reinforcement Learning

What Can RL Bring to VLA Generalization? An Empirical Study

2025-05-26 · Jijia Liu, Feng Gao, Bingwen Wei, Xinlei Chen 외

Large Vision-Language Action (VLA) models have shown significant potential for embodied AI. However, their predominant training via supervised fine-tuning (SFT) limits generalization due to susceptibility to compounding …

Reinforcement Learning (RL)Vision-Language-Action

KAGE-Bench: Fast Known-Axis Visual Generalization Evaluation for Reinforcement Learning

2026-01-20 · Egor Cherepanov, Daniil Zelezetsky, Alexey K. Kovalev, Aleksandr I. Panov arxiv

Pixel-based reinforcement learning agents often fail under purely visual distribution shift even when latent dynamics and rewards are unchanged, but existing benchmarks entangle multiple sources of shift and hinder syste…

Reinforcement Learning

Obstacle Tower Without Human Demonstrations: How Far a Deep Feed-Forward Network Goes with Reinforcement Learning

2020-04-01 · Marco Pleines, Jenia Jitsev, Mike Preuss, Frank Zimmer

The Obstacle Tower Challenge is the task to master a procedurally generated chain of levels that subsequently get harder to complete. Whereas the most top performing entries of last year's competition used human demonstr…

Deep Reinforcement LearningReinforcement Learning

Daylight: Assessing Generalization Skills of Deep Reinforcement Learning Agents

2021-01-01 · Ezgi Korkmaz

Deep reinforcement learning algorithms have recently achieved significant success in learning high-performing policies from purely visual observations. The ability to perform end-to-end learning from raw high dimensional…

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)