Learning What Matters: Adaptive Information-Theoretic Objectives for Robot Exploration

arXiv:2605.12084 · cs.RO, cs.AI, cs.IT, cs.LG, cs.SY, eess.SY, math.IT · Submitted 2026-05-12 · Read on arXiv

cs.RO, cs.AI, cs.IT, cs.LG, cs.SY, eess.SY, math.IT

Submitted: 2026-05-12

Updated: 2026-05-12

Project page: https://www.youwei-yu.com/qoed

Terminology

• Fisher Information — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes

Sources

• FisherRF: Active View Selection and Uncertainty Quantification for Radiance Fields using Fisher Information
• Sampling-Based System Identification with Active Exploration for Legged Robot Sim2Real Learning
• Efficient exploration with Double Uncertain Value Networks
• DORA The Explorer: Directed Outreaching Reinforcement Action-Selection
• Exploration by Random Network Distillation
• Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models
• Learning to Perform Physics Experiments via Deep Reinforcement Learning
• Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Robotics
• Proximal Policy Optimization Algorithms

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• ARC: A Reasoning Recipe for Robot Foundation Models
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies