paper-with-me

홈 › Papers

Tackling Visual Control via Multi-View Exploration Maximization

2022-11-28 · Mingqi Yuan, Xin Jin, Bo Li, Wenjun Zeng

We present MEM: Multi-view Exploration Maximization for tackling complex visual control tasks. To the best of our knowledge, MEM is the first approach that combines multi-view representation learning and intrinsic reward-driven exploration in reinforcement learning (RL). More specifically, MEM first extracts the specific and shared information of multi-view observations to form high-quality features before performing RL on the learned features, enabling the agent to fully comprehend the environment and yield better actions. Furthermore, MEM transforms the multi-view features into intrinsic rewards based on entropy maximization to encourage exploration. As a result, MEM can significantly promote the sample-efficiency and generalization ability of the RL agent, facilitating solving real-world problems with high-dimensional observations and spare-reward space. We evaluate MEM on various tasks from DeepMind Control Suite and Procgen games. Extensive simulation results demonstrate that MEM can achieve superior performance and outperform the benchmarking schemes with simple architecture and higher efficiency.

📄 PDF Abstract BibTeX arXiv:2211.15233

Code (0)

등록된 구현이 없습니다.

Tasks

BenchmarkingReinforcement Learning (RL)Representation Learning

Similar Papers 제목 키워드 기반

REALMS2 -- Resilient Exploration And Lunar Mapping System 2 -- A Comprehensive Approach

2025-10-30 · Dave van der Meer, Loïck P. Chovet, Gabriel M. Garcia, Abhishek Bera 외 arxiv

The European Space Agency (ESA) and the European Space Resources Innovation Centre (ESRIC) created the Space Resources Challenge to invite researchers and companies to propose innovative solutions for Multi-Robot Systems…

Designing streetscapes from street-view imagery using diffusion models

2026-05-17 · Yuzhou Chen, Yuebing Liang, Lingqian Hu, Kailai Sun 외 arxiv

Street-view imagery (SVI) is widely used to quantify key indicators of urban environment, such as green- ery, sky, or road view indices. However, existing studies largely focus on measuring current streetscapes and rarel…

Scene Generation

Learning Efficient Multi-Agent Cooperative Visual Exploration

2021-10-12 · Chao Yu, Xinyi Yang, Jiaxuan Gao, Huazhong Yang 외

We tackle the problem of cooperative visual exploration where multiple agents need to jointly explore unseen regions as fast as possible based on visual signals. Classical planning-based methods often suffer from expensi…

Reinforcement Learning (RL)Visual Navigation

Augmenting Control over Exploration Space in Molecular Dynamics Simulators to Streamline De Novo Analysis through Generative Control Policies

2023-06-26 · Paloma Gonzalez-Rojas, Andrew Emmel, Luis Martinez, Neil Malur 외

This study introduces the P5 model - a foundational method that utilizes reinforcement learning (RL) to augment control, effectiveness, and scalability in molecular dynamics simulations (MD). Our innovative strategy opti…

Drug DiscoveryInductive BiasReinforcement Learning (RL)

WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory

2026-09-21 · Wangbo Yu, Kunhao Liu, Wenbo Hu, Shenghai Yuan 외 hf

Video world models enable interactive exploration of dynamic environments, yet struggle to respect prior observations over long horizons and across viewpoints. We present WorldCrafter, a video world model that learns a c…