Entity · paper

Active Offline-to-Online Reinforcement Learning

paperactiveprovisionalactive-offline-to-online-reinforcement-learning-ef39c1a7·1 events·first seen Jul 14, 2026

Aliases: Active Offline-to-Online Reinforcement Learning

More like this (12)

Reinforcement Learning Physics-EnhAnced Reinforcement Learning decoupled reinforcement learning sim-to-real reinforcement learning shielded reinforcement learning Multi-Agent Reinforcement Learning from Delayed Marketplace Feedback for Objective-Weight Adaptation in Three-Sided Dispatch Hierarchical Advantage Weighting for Online RL Fine-Tuning of VLAs from Sparse Episode Outcomes Reinforcement Learning for Code UniIntervene: Agentic Intervention for Efficient Real-World Reinforcement Learning Entropy-Regularized Reinforcement Learning Generalization in offline RL: The structure is more important than the amount of pessimism Pessimism's Paradox: Conservative Offline Training Amplifies Reward Hacking During Online Adaptation in Reasoning Models

Recent events (1)

4arXiv · cs.AI·Jul 14, 2026·source ↗

Active policy selection for offline-to-online RL fine-tuning under limited interaction budgets

A new arXiv preprint introduces an active policy selection framework for offline-to-online reinforcement learning (O2O-RL), addressing the problem of choosing which candidate policy to fine-tune when online interactions are scarce or risky. The method uses upper-confidence bounds derived from locally linear performance forecasts to balance exploration (policy evaluation) against exploitation (fine-tuning). Experiments show consistent outperformance over existing O2O-RL baselines. The authors claim this is the first work to formally address active policy selection in the O2O-RL setting.

AI Safety Research Active Offline-to-Online Reinforcement Learning