DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization

2 code implementations • 30 Oct 2023 • Guowei Xu, Ruijie Zheng, Yongyuan Liang, Xiyao Wang, Zhecheng Yuan, Tianying Ji, Yu Luo, Xiaoyu Liu, Jiaxin Yuan, Pu Hua, Shuzhen Li, Yanjie Ze, Hal Daumé III, Furong Huang, Huazhe Xu

To quantify this inactivity, we adopt dormant ratio as a metric to measure inactivity in the RL agent's network.

Continuous Control reinforcement-learning +1

RL-ViGen: A Reinforcement Learning Benchmark for Visual Generalization

1 code implementation • NeurIPS 2023 • Zhecheng Yuan, Sizhe Yang, Pu Hua, Can Chang, Kaizhe Hu, Huazhe Xu

Visual Reinforcement Learning (Visual RL), coupled with high-dimensional observations, has consistently confronted the long-standing challenge of out-of-distribution generalization.

Out-of-Distribution Generalization reinforcement-learning

Simple Emergent Action Representations from Multi-Task Policy Training

no code implementations • 18 Oct 2022 • Pu Hua, Yubei Chen, Huazhe Xu

The low-level sensory and motor signals in deep reinforcement learning, which exist in high-dimensional spaces such as image observations or motor torques, are inherently challenging to understand or utilize directly for downstream tasks.