16 citations · 17 across the 7 of their papers we have counts for
7 papers
Subspace Inference Enables Efficient Active Reward Learning from Preferences
Yutai Zhou, Erdem Bıyık
Reinforcement learning from human feedback (RLHF) has emerged as a powerful yet sample-inefficient approach for learning reward models from human preferences, making active learnin…
AutoFocus-IL: VLM-based Saliency Maps for Data-Efficient Visual Imitation Learning without Extra Human Annotations
Litian Gong, Fatemeh Bahrani, Yutai Zhou +3
AutoFocus-IL is a simple yet effective method to improve data efficiency and generalization in visual imitation learning by guiding policies to attend to task-relevant features rat…
GABRIL: Gaze-Based Regularization for Mitigating Causal Confusion in Imitation Learning
Amin Banayeeanzade, Fatemeh Bahrani, Yutai Zhou +1
Imitation Learning (IL) is a widely adopted approach which enables agents to learn from human expert demonstrations by framing the task as a supervised learning problem. However, I…
CLAM: Continuous Latent Action Models for Robot Learning from Unlabeled Demonstrations
Anthony Liang, Pavel Czempin, Matthew M. Hong +4
Learning robot control policies from demonstrations typically requires action-labeled expert data, which is expensive to collect through teleoperation. We study a more practical se…
In Pursuit of Predictive Models of Human Preferences Toward AI Teammates
Ho Chit Siu, Jaime D. Peña, Yutai Zhou +1
We seek measurable properties of AI agents that make them better or worse teammates from the subjective perspective of human collaborators. Our experiments use the cooperative card…
Evaluation of Human-AI Teams for Learned and Rule-Based Agents in Hanabi
Ho Chit Siu, Jaime D. Pena, Edenna Chen +5
Deep reinforcement learning has generated superhuman AI in competitive games such as Go and StarCraft. Can similar learning techniques create a superior AI teammate for human-machi…
Learning Emergent Discrete Message Communication for Cooperative Reinforcement Learning
Sheng Li, Yutai Zhou, Ross Allen +1
Communication is a important factor that enables agents work cooperatively in multi-agent reinforcement learning (MARL). Most previous work uses continuous message communication wh…