RL-ViGen: A Reinforcement Learning Benchmark for Visual Generalization
Authors:
- Zhecheng YuanZYZhecheng Yuan
- Kaizhe HuKHKaizhe Hu
- Huazhe XuHXHuazhe Xu
Preprint
Abstract
Visual Reinforcement Learning (Visual RL), coupled with high-dimensional observations, has consistently confronted the long-standing challenge of generalization. Despite the focus on algorithms aimed at resolving visual generalization problems, we argue that the devil is in the existing benchmarks as they are restricted to isolated tasks and generalization categories, undermining a comprehensive evaluation of agents' visual generalization capabilities. To bridge this gap, we introduce RL-ViGen: a novel Reinforcement Learning Benchmark for Visual Generalization, which contains diverse tasks and a wide spectrum of generalization types, thereby facilitating the derivation of more reliable conclusions. Furthermore, RL-ViGen incorporates the latest generalization visual RL algorithms into a unified framework, under which the experiment results indicate that no single existing algorithm has prevailed universally across tasks. Our aspiration is that RL-ViGen will serve as a catalyst in this area, and lay a foundation for the future creation of universal visual generalization RL agents suitable for real-world scenarios. Access to our code and implemented algorithms is provided at https://gemcollector.github.io/RL-ViGen/.Keywords
All Related Versions
This publication has 5 references indexed in Scilit:
- Dense reinforcement learning for safety validation of autonomous vehiclesNature, 2023
- A Survey of Zero-shot Generalisation in Deep Reinforcement LearningJournal of Artificial Intelligence Research, 2023
- Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations2018
- MuJoCo: A physics engine for model-based control2012
- Operational Space Control: A Theoretical and Empirical ComparisonThe International Journal of Robotics Research, 2008