Research map / Reinforcement learning / Visual and representation RL
Novel Exploration via Orthogonality
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Introduces NEO (Novel Exploration via Orthogonality), an exploration approach for reinforcement learning that aims to identify both which regions of the environment are novel and how to reach them.
Problem
Efficient exploration in reinforcement learning, where agents must discover novel states or transitions without revisiting already well-explored regions of the state space.
Approach
NEO automatically uncovers not only which regions of the environment are novel but also how to reach them, using orthogonality to direct the policy away from well-explored regions.
Closest papers by meaning
- The Laplacian Keyboard: Beyond the Linear Span (NeurIPS 2026 · similarity 0.88)
- Online Laplacian-Based Representation Learning in Reinforcement Learning (ICML 2025 · similarity 0.87)
- Proper Laplacian Representation Learning (ICLR 2024 · similarity 0.87)
- Geometric Active Exploration in Markov Decision Processes: the Benefit of Abstraction (ICML 2024 · similarity 0.87)
- Efficient Exploration and Discriminative World Model Learning with an Object-Centric Abstraction (ICLR 2025 · similarity 0.86)
- Scalable Online Exploration via Coverability (ICML 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.