Research map / Reinforcement learning / MDPs and planning

Deployment Efficient Reward-Free Exploration with Linear Function Approximation

NeurIPS 2025 · Reinforcement learning › MDPs and planning · approach: Offline RL sample complexity · 0 citations (OpenAlex)

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.

Studies deployment-efficient reward-free exploration in linear MDPs, aiming to explore without reward feedback while minimizing the number of distinct policies deployed.

Problem

Reward-free exploration in linear MDPs where the number of distinct policies deployed during learning should be small, since deploying many policies is costly in real-world applications.

Approach

Designs reward-free exploration algorithms for linear function approximation whose number of deployments is small; the abstract only indicates the goal of minimizing distinct deployed policies, so the specific mechanism is not stated.

Closest papers by meaning

• Near-Optimal Deployment Efficiency in Reward-Free Reinforcement Learning with Linear Function Approximation (ICLR 2023 · similarity 0.95)
• Reward-Free Exploration for Reinforcement Learning (ICML 2020 · similarity 0.92)
• Towards Minimax Optimal Reward-free Reinforcement Learning in Linear MDPs (ICLR 2023 · similarity 0.92)
• Reward-Free RL is No Harder Than Reward-Aware RL in Linear Markov Decision Processes (ICML 2022 · similarity 0.92)
• Scalable Online Exploration via Coverability (ICML 2024 · similarity 0.91)
• Reward-Free Kernel-Based Reinforcement Learning (ICML 2024 · similarity 0.88)