6 papers
STATe-of-Thoughts: Structured Action Templates for Tree-of-Thoughts
Zachary Bamberger, Till R. Saenger, Gilad Morad +3
Inference-Time-Compute (ITC) methods like Best-of- and Tree-of-Thoughts are meant to produce output candidates that are both high-quality and diverse, but their use of high-temp…
From Actions to Words: Towards Abstractive-Textual Policy Summarization in RL
Sahar Admoni, Assaf Hallak, Yftah Ziser +2
Explaining reinforcement learning agents is challenging because policies emerge from complex reward structures and neural representations that are difficult for humans to interpret…
Assessing Policy Updates: Toward Trust-Preserving Intelligent User Interfaces
Matan Solomon, Ofra Amir, Omer Ben-Porat
Reinforcement learning agents are often updated with human feedback, yet such updates can be unreliable: reward misspecification, preference conflicts, or limited data may leave po…
Gap the (Theory of) Mind: Sharing Beliefs About Teammates' Goals Boosts Collaboration Perception, Not Performance
Yotam Amitai, Reuth Mirsky, Ofra Amir
In human-agent teams, openly sharing goals is often assumed to enhance planning, collaboration, and effectiveness. However, direct communication of these goals is not always feasib…
"Trust me on this" Explaining Agent Behavior to a Human Terminator
Uri Menkes, Assaf Hallak, Ofra Amir
Consider a setting where a pre-trained agent is operating in an environment and a human operator can decide to temporarily terminate its operation and take-over for some duration o…
Interactive Explanations for Reinforcement-Learning Agents
Yotam Amitai, Ofra Amir, Guy Avni
As reinforcement learning methods increasingly amass accomplishments, the need for comprehending their solutions becomes more crucial. Most explainable reinforcement learning (XRL)…