Behavioral Exploration: Learning to Explore via In-Context Adaptation | HTML5

Developing autonomous agents that quickly explore an environment and adapt their behavior online is a canonical challenge in robotics and machine learning. While humans are able to achieve such fast online exploration …

Behavioral Exploration: Learning to Explore via In-Context Adaptation Andrew Wagenmaker Zhiyuan Zhou Sergey Levine Abstract Developing autonomous agents that quickly explore an environment and adapt their behavior online is a canonical challenge in robotics and machine learning. While humans are able to achieve such fast online exploration and adaptation, often acquiring new information and skills in only a handful of interactions, existing algorithmic approaches tend to rely on random exploration and slow, gradient-based behavior updates. How can we endow autonomous agents with such capabilit

related reading

• State of Robot Learning, December 2025vedder.io
• [2507.09061] Action Chunking and Exploratory Data Collection Yield Exponential Improvements in Behavior Cloning for Continuous Controlarxiv.org
• Exploration for the Efficient Deployment of Reinforcement Learning Agentsopenreview.net
• [2506.22401] Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RLarxiv.org
• 2109.10813.pdfarxiv.org
• [1709.06560] Deep Reinforcement Learning that Mattersarxiv.org
• Is Curiosity All You Need? On the Utility of Emergent Behaviours from Curious Explorationarxiv.org
• [2109.01115] Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotationarxiv.org
• Ch. 21 - Imitation Learningunderactuated.mit.edu
• [2103.06326] S4RL: Surprisingly Simple Self-Supervision for Offline Reinforcement Learningarxiv.org
• [2606.09758] Difference-Aware Retrieval Policies for Imitation Learningarxiv.org
• [2206.11795] Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videosarxiv.org