Visual Reinforcement Learning

Visual reinforcement learning (VRL) aims to train agents to make decisions and control actions directly from visual inputs, a challenging problem due to the high dimensionality and complexity of visual data. Current research heavily focuses on improving sample efficiency and generalization capabilities, employing techniques like contrastive learning, knowledge distillation, and data augmentation within various model architectures including convolutional neural networks and transformers. These advancements are crucial for enabling robots and autonomous systems to learn complex tasks from visual experience, impacting fields like robotics, autonomous driving, and video game AI.

Papers

December 28, 2023

Generalizable Visual Reinforcement Learning with Segment Anything Model
Ziyu Wang, Yanjie Ze, Yifei Sun, Zhecheng Yuan, Huazhe Xu
Reinforcement Learning Segment Anything Model Promptable Segmentation Visual Reinforcement Learning Visual Generalization

December 4, 2023

A Reliable Representation with Bidirectional Transition Model for Visual Reinforcement Learning Generalization
Xiaobo Hu, Youfang Lin, Yue Liu, Jinwen Wang, Shuo Wang, Hehe Fan, Kai Lv
Reinforcement Learning Visual Reinforcement Learning Generalizable Representation Bidirectional Correspondence Bidirectional Generation DeepMind Control Suite Reliable Representation

November 22, 2023

Evaluating Pretrained models for Deployable Lifelong Learning
Kiran Lekkala, Eshan Bhargava, Yunhao Ge, Laurent Itti
Full Model Continual LEArning Lifelong Learning Visual Reinforcement Learning Lifelong Learning System

October 30, 2023

DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization
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, Furong Huang, Huazhe Xu
Active Exploration Visual Reinforcement Learning Exploration Exploitation Trade Continuous Control Task

October 11, 2023

Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stages
Guozheng Ma, Lu Li, Sen Zhang, Zixuan Liu, Zhen Wang, Yixin Chen, Li Shen, Xueqian Wang, Dacheng Tao
Raw Data Sample Efficient Plasticity Rule Dynamic ModulE Visual Reinforcement Learning Plasticity Loss

October 10, 2023

EARL: Eye-on-Hand Reinforcement Learner for Dynamic Grasping with Active Pose Estimation
Baichuan Huang, Jingjin Yu, Siddarth Jain
Pose Estimation Vision Based Visual Reinforcement Learning Dynamic Grasping Robust Grasp

October 8, 2023

Learning Generalizable Agents via Saliency-Guided Features Decorrelation
Sili Huang, Yanchao Sun, Jifeng Hu, Siyuan Guo, Hechang Chen, Yi Chang, Lichao Sun, Bo Yang
Saliency Map Visual Reinforcement Learning Generalist Agent Feature Decorrelation Task Specific Feature

October 2, 2023

H-InDex: Visual Reinforcement Learning with Hand-Informed Representations for Dexterous Manipulation
Yanjie Ze, Yuyao Liu, Ruizhe Shi, Jiaxin Qin, Zhecheng Yuan, Jiashun Wang, Huazhe Xu
Robotic Manipulation Visual Representation Learning Dexterous Manipulation Pre Trained Representation 3D Hand Visual Reinforcement Learning Hand Object

September 22, 2023

Sequential Action-Induced Invariant Representation for Reinforcement Learning
Dayang Liang, Qihang Chen, Yunlong Liu
Reinforcement Learning Action Representation Sequential Information Visual Reinforcement Learning DeepMind Control Suite Task Relevant State

August 2, 2023

Improving Generalization in Visual Reinforcement Learning via Conflict-aware Gradient Agreement Augmentation
Siao Liu, Zhaoyu Chen, Yang Liu, Yuzheng Wang, Dingkang Yang, Zhile Zhao, Ziqing Zhou, Xie Yi, Wei Li, Wenqiang Zhang, Zhongxue Gan
Strong Generalization Policy Gradient Visual Reinforcement Learning Gradient Consistency Data Augmentation Consistency Regularization

July 15, 2023

RL-ViGen: A Reinforcement Learning Benchmark for Visual Generalization
Zhecheng Yuan, Sizhe Yang, Pu Hua, Can Chang, Kaizhe Hu, Huazhe Xu
Reinforcement Learning Reinforcement Learning Benchmark Visual Reinforcement Learning Visual Generalization Rl Msa

July 3, 2023

MoVie: Visual Model-Based Policy Adaptation for View Generalization
Sizhe Yang, Yanjie Ze, Huazhe Xu
Strong Generalization Real World Reward Signal Visual Reinforcement Learning Movie Review

June 22, 2023

June 11, 2023

On the Efficacy of 3D Point Cloud Reinforcement Learning
Zhan Ling, Yunchao Yao, Xuanlin Li, Hao Su
3d Representation Visual Reinforcement Learning

June 1, 2023

Normalization Enhances Generalization in Visual Reinforcement Learning
Lu Li, Jiafei Lyu, Guozheng Ma, Zilin Wang, Zhenjie Yang, Xiu Li, Zhiheng Li
Reinforcement Learning Generalization Performance Visual Reinforcement Learning Feature Normalization

May 25, 2023

Learning Better with Less: Effective Augmentation for Sample-Efficient Visual Reinforcement Learning
Guozheng Ma, Linrui Zhang, Haoyu Wang, Lu Li, Zilin Wang, Zhen Wang, Li Shen, Xueqian Wang, Dacheng Tao
Data Augmentation Sample Efficient Visual Reinforcement Learning Continual Learner Effective Augmentation

February 19, 2023

Generalization in Visual Reinforcement Learning with the Reward Sequence Distribution
Jie Wang, Rui Yang, Zijie Geng, Zhihao Shi, Mingxuan Ye, Qi Zhou, Shuiwang Ji, Bin Li, Yongdong Zhang, Feng Wu
Strong Generalization Markov Decision Process State Space Visual Reinforcement Learning Partially Observed Markov Decision Process Reward Distribution

February 12, 2023

Robust Representation Learning by Clustering with Bisimulation Metrics for Visual Reinforcement Learning with Distractions
Qiyuan Liu, Qi Zhou, Rui Yang, Jie Wang
Representation Learning Visual Reinforcement Learning Sample Efficient Reinforcement Learning Robust Representation Learning Bisimulation Metric Distraction Level Behavioral Similarity

December 17, 2022

Pre-Trained Image Encoder for Generalizable Visual Reinforcement Learning
Zhecheng Yuan, Zhengrong Xue, Bo Yuan, Xueqian Wang, Yi Wu, Yang Gao, Huazhe Xu
Reinforcement Learning Pre Trained Visual Representation Visual Reinforcement Learning Generalizable Representation