Video here.ĩ/15/21 - Our paper ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learning was accepted to CoRL 2021.Ĩ/10/21 - Our workshop on Safe and Robust Control of Uncertain Systems was accepted to NeurIPS 2021.Ħ/14/21 - Our paper on Offline Preference-Based Apprenticeship Learning was accepted at the ICML Workshop on Human-AI Collaboration in Sequential Decision-Making.Ħ/10/21 - I was selected as a 2021 RSS Pioneer.Ħ/4/21 - Two papers accepted to IEEE CASE 2021: LazyDAgger: Reducing Context Switching in Interactive Imitation Learning and Kit-Net: Self-Supervised Learning to Kit Novel 3D Objects into Novel 3D Cavities.ĥ/29/21 - Two papers accepted to ICML 2021: Value Alignment Verification and Policy Gradient Bayesian Robust Optimization for Imitation Learning.ĥ/20/21 - I gave a talk at UC Berkeley's Midday Science Cafe on "Harnessing Machine Learning for Science," with a focus on how robots can learn from, model, and better assist humans. Video here.ġ0/1/21 - I was an invited speaker on the Talking Robotics virtual seminar series. ![]() ![]() 11/25/22 - Our paper The Effect of Modeling Human Rationality Level on Learning Rewards from Multiple Feedback Types was accepted to the AAAI 2023!ġ1/14/22 - Our paper Interpretable Reward Learning via Differentiable Decision Trees has been accepted to the NeurIPS 2022 ML Safety Workshop!ġ1/14/22 - Our paper "Efficient Preference-Based Reinforcement Learning Using Learned Dynamics Models" has been accepted to the NeurIPS 2022 Workshop on Human in the Loop Learning!ĩ/14/22 - Our paper Monte Carlo Augmented Actor-Critic for Sparse Reward Deep Reinforcement Learning from Suboptimal Demonstrations has been accepted to NeurIPS 2022!ĩ/10/22 - Our paper Learning Representations that Enable Generalization in Assistive Tasks has been accepted to CoRL 2022!Ĩ/13/22 - Initial course website is up for my Fall 2022 class: Human-AI Alignment.Ĩ/2/22 - Our paper Teaching Robots to Span the Space of Functional Expressive Motion was accepted to IROS 2022.ħ/1/22 - I started as an assistant professor at the University of Utah's Robotics Center and School of Computing.ĥ/25/22 - Our paper Study of Causal Confusion in Preference-Based Reward Learning has been accepted to the RSS 2022 Workshop Overlooked Aspects of Imitation Learning: Systems, Data, Tasks, and Beyond.ĥ/25/22 - Our paper Learning Switching Criteria for Sim2Real Transfer of Robotic Fabric Manipulation Policies was accepted to CASE 2022.ĥ/6/22 - I gave at talk at the Stanford Robotics Seminar on "Leveraging Human Input to Enable Robust AI Systems".ģ/30/22 - I accepted a position as an assistant professor at the School of Computing and Robotics Center at the University of Utah starting all 2022!ġ/31/21 - Our paper LEGS: Learning Efficient Grasp Sets for Exploratory Grasping was accepted at ICRA 2022!ġ0/15/21 - I gave an AI Seminar on "Efficient and Robust Learning of Human Intent" at U.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |