Research map / Reinforcement learning / Visual and representation RL

Addressing Sparse-Rewards in RL with Scalable Hierarchical Novel Eigen Options

NeurIPS 2026 · Reinforcement learning › Visual and representation RL · approach: Reward shaping for sparse rewards

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.

Proposes a scalable hierarchical extension of NEO (Novel Exploration via Orthogonality) that learns novel eigen options for sparse-reward RL in pixel-based domains under function approximation.

Problem

Exploration in sparse-reward RL: existing graph Laplacian-based temporally extended options either do not explicitly target novelty or fail to scale to pixel-based domains with function approximation.

Approach

Builds on NEO, which constructs options that navigate from highly visited regions toward less visited ones, and makes it scalable and hierarchical so it works with pixel observations under function approximation.

Experimental setup

Builds on: NEO (Novel Exploration via Orthogonality)

Closest papers by meaning

• Novel Exploration via Orthogonality (NeurIPS 2025 · similarity 0.93)
• The Laplacian Keyboard: Beyond the Linear Span (NeurIPS 2026 · similarity 0.90)
• DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning (NeurIPS 2025 · similarity 0.90)
• Online Laplacian-Based Representation Learning in Reinforcement Learning (ICML 2025 · similarity 0.88)
• Reward-Free Kernel-Based Reinforcement Learning (ICML 2024 · similarity 0.88)
• Uncertainty-Aware Reward-Free Exploration with General Function Approximation (ICML 2024 · similarity 0.88)