Learning to Visually Navigate in Photorealistic Environments Without any Supervision
원문 초록
Learning to navigate in a realistic setting where an agent must rely solely on visual inputs is a challenging task, in part because the lack of position information makes it difficult to provide supervision during training. In this paper, we introduce a novel approach for learning to navigate from image inputs without external supervision or reward. Our approach consists of three stages: learning a good representation of first-person views, then learning to explore using memory, and finally learning to navigate by setting its own goals. The model is trained with intrinsic rewards only so that it can be applied to any environment with image observations. We show the benefits of our approach by training an agent to navigate challenging photo-realistic environments from the Gibson dataset with RGB inputs only.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Position: Olfaction Standardization is Essential for the Advancement of Embodied Artificial Intelligence
Optimization Problem Solving Can Transition to Evolutionary Agentic Workflows
Multidimensional Particle Filter for Long-Term Visual Teach and Repeat in Changing Environments
Car Object Counting and Position Estimation via Extension of the CLIP-EBC Framework
STRUCTSENSE: A Task-Agnostic Agentic Framework for Structured Information Extraction with Human-In-The-Loop Evaluation and Benchmarking
AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench
토론
이 논문과 연결된 포럼 글이 아직 없습니다.