paper
UniIntervene: Agentic Intervention for Efficient Real-World Reinforcement Learning
paperactiveprovisional
uniintervene-agentic-intervention-for-efficient-real-world-reinforcement-learning-09d9248f·1 events·first seen 6d agoAliases: UniIntervene: Agentic Intervention for Efficient Real-World Reinforcement Learning
Co-occurring entities
More like this (12)
UniInterveneUsing Reward Uncertainty to Induce Diverse Behaviour in Reinforcement LearningReinforcement Learningsim-to-real reinforcement learningshielded reinforcement learningdecoupled reinforcement learningExpRL: Exploratory RL for LLM Mid-TrainingAPPO: Agentic Procedural Policy OptimizationAgentic RLReward Modeling for Multi-Agent OrchestrationEntropy-Regularized Reinforcement LearningMulti-Agent Reinforcement Learning from Delayed Marketplace Feedback for Objective-Weight Adaptation in Three-Sided Dispatch
Recent events (1)
UniIntervene: Agentic model reduces human interventions in real-world robot RL by 57%
UniIntervene is a proposed agentic intervention model for human-in-the-loop reinforcement learning (HiL-RL) that autonomously detects unproductive exploration and recovers robot policies toward high-value states, replacing the bulk of human corrections. The system uses future-conditioned action-value estimation, a temporal value-risk critic, and a goal-conditioned recovery policy drawing from a memory of past interventions. Experiments on real-world robotic manipulation tasks show a 57% reduction in human interventions and an 8.6% improvement in average success rate over state-of-the-art HiL-RL baselines.