- Dec 1, 2025: We were interviewed by journalists from Donga Science, the longest-running science magazine of South Korea, for our work ReWiND. Access the interview here.
- Oct 15, 2025: Our paper titled "Active Reward Learning and Iterative Trajectory Improvement from Comparative Language Feedback" got accepted to the International Journal of Robotics Research (IJRR).
- Sep 24, 2025: Our paper titled "Training Robots with Natural and Lightweight Human Feedback" got accepted for publication at the AI Magazine. It summarizes some of the projects that we pursuse in the lab.
- Sep 18, 2025: Our paper titled "Actor-Free Continuous Control via Structurally Maximizable Q-Functions" got accepted to the 39th Conference on Neural Information Processing Systems (NeurIPS) 2025.
- Aug 7, 2025: Our paper "Mitigating Suboptimality of Deterministic Policy Gradients in Complex Q-functions" received the "Outstanding Paper Award on Empirical Reinforcement Learning Research" at RLC 2025.
- Aug 1, 2025: Our paper titled "ReWiND: Language-Guided Rewards Teach Robot Policies without New Demonstrations" got accepted to the Conference on Robot Learning (CoRL) 2025 as an oral presentation.
- Jul 10, 2025: Yutai Zhou has been named a Capital One Fellow!
- Jun 26, 2025: Our paper "ReWiND: Language-Guided Rewards Teach Robot Policies without New Demonstrations" received the best paper award among ~50 papers at the "2nd Workshop on Out-of-Distribution Generalization in Robotics" at RSS 2025. It was also nominated for the best paper award at the "Workshop on Learned Robot Representations" at RSS 2025.
- Jun 15, 2025: Our 2 papers got accepted to the 2025 International Conference on Intelligent Robots and Systems (IROS).:
- GABRIL: Gaze-Based Regularization for Mitigating Causal Confusion in Imitation Learning
- RAILGUN: A Unified Convolutional Policy for Multi-Agent Path Finding Across Different Environments and Tasks
- May 9, 2025: Our paper titled "Mitigating Suboptimality of Deterministic Policy Gradients in Complex Q-functions" got accepted to the Reinforcement Learning Conference (RLC) 2025.
- Apr 29, 2025: Matthew Hong has received the Best MS Research Award of Thomas Lord Department of Computer Science! This award is given to only two students every year.
- Apr 10, 2025: Our paper titled "NaVILA: Legged Robot Vision-Language-Action Model for Navigation" got accepted to the Robotics: Science and Systems (RSS) 2025 conference.
- Mar 21, 2025: We are organizing a workshop on human-in-the-loop robot learning at RSS 2025. Check it out here for more details.
- Jan 27, 2025: Our 2 papers got accepted to the 2025 International Conference on Robotics and Automation (ICRA):
- MILE: Model-based Intervention Learning
- Multi-Agent Inverse Q-Learning from Demonstrations
- Dec 19, 2024: Our paper titled "Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback" has been selected as a finalist for TMLR's 2024 outstanding papers.
- Sep 25, 2024: Our paper titled "DynaMITE-RL: A Dynamic Model for Improved Temporal Meta-Reinforcement Learning" got accepted to the 38th Conference on Neural Information Processing Systems (NeurIPS).
- Sep 20, 2024: Our paper titled "Accurate and Data-Efficient Toxicity Prediction when Annotators Disagree" got accepted to the Conference on Empirical Methods in Natural Language Processing (EMNLP).
- Sep 4, 2024: Our 2 papers got accepted to the Conference on Robot Learning (CoRL) 2024:
- Trajectory Improvement and Reward Learning from Comparative Language Feedback
- EXTRACT: Efficient Policy Learning by Extracting Transferable Robot Skills from Offline Data
- Jun 30, 2024: Our paper titled "ViSaRL: Visual Reinforcement Learning Guided by Human Saliency" got accepted to the 2024 International Conference on Intelligent Robots and Systems (IROS).
- May 2, 2024: Our 2 papers got accepted to the 2024 International Conference on Machine Learning (ICML):
- RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedback
- Coprocessor Actor Critic: A Model-Based Reinforcement Learning Approach For Adaptive Brain Stimulation
- Feb 20, 2024: Our paper titled "Batch Active Learning of Reward Functions from Human Preferences" got accepted to the ACM Transactions on Human-Robot Interaction (THRI).
- Jan 30, 2024: Our paper titled "A Generalized Acquisition Function for Preference-based Reward Learning" got accepted to the 2024 International Conference on Robotics and Automation (ICRA).
- Dec 5, 2023: Our paper titled "Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback" got accepted to the Transactions on Machine Learning Research (TMLR).
- Sep 25, 2023: Our paper titled "Active Preference-Based Gaussian Process Regression for Reward Learning and Optimization" got accepted to the International Journal of Robotics Research (IJRR).
- Sep 21, 2023: Our paper titled "RoboCLIP: One Demonstration is Enough to Learn Robot Policies" got accepted to the 37th Conference on Neural Information Processing Systems (NeurIPS).
- Jan 30, 2023: Our paper titled "Active Reward Learning from Online Preferences" got accepted to the 2023 International Conference on Robotics and Automation (ICRA).
- Sep 15, 2022: Our paper titled "Assistive Teaching of Motor Control Tasks to Humans" got accepted to the 36th Conference on Neural Information Processing Systems (NeurIPS).
- Apr 12, 2022: Our paper titled "How do People Incorporate Advice from Artificial Agents when Making Physical Judgments?" got accepted to the 2022 Cognitive Science Society Conference (CogSci).
- Jan 31, 2022: Our paper titled "Leveraging Smooth Attention Prior for Multi-Agent Trajectory Prediction" got accepted to the 2022 International Conference on Robotics and Automation (ICRA).
- Jan 6, 2022: Our paper titled "APReL: A Library for Active Preference-based Reward Learning Algorithms" got accepted to the 17th ACM/IEEE International Conference on Human-Robot Interaction (HRI).
- Dec 16, 2021: Our paper titled "Partner-Aware Algorithms in Decentralized Cooperative Bandit Teams" got accepted to the 36th AAAI Conference on Artificial Intelligence.
- Sep 13, 2021: Our 2 papers got accepted to the 5th Conference on Robot Learning (CoRL):
- Learning Multimodal Rewards from Rankings
- Learning Reward Functions from Scale Feedback
- Sep 9, 2021: Our 2 papers got accepted to the Artificial Intelligence for Human-Robot Interaction (AI-HRI) at AAAI Fall Symposium Series:
- Partner-Aware Algorithms in Decentralized Cooperative Bandit Teams
- APReL: A Library for Active Preference-based Reward Learning Algorithms
- Aug 15, 2021: We have released our Python library APReL, which unifies active preference-based reward learning algorithms.
- Aug 4, 2021: Our paper titled "Learning Reward Functions from Diverse Sources of Human Feedback: Optimally Integrating Demonstrations and Preferences" got accepted to The International Journal of Robotics Research (IJRR).
- Jul 9, 2021: Our paper titled "Learning How to Dynamically Route Autonomous Vehicles on Shared Roads" got accepted to Transportation Research Part C: Emerging Technologies (TR_C).
- May 18, 2021: Our paper titled "Emergent Prosociality in Multi-Agent Games Through Gifting" got accepted to the 30th International Joint Conference on Artificial Intelligence (IJCAI).
- May 5, 2021: Our paper titled "Incentivizing Efficient Equilibria in Traffic Networks with Mixed Autonomy" got accepted to the IEEE Transactions on Control of Network Systems (TCNS).
- Feb 28, 2020: Our paper titled "ROIAL: Region of Interest Active Learning for Characterizing Exoskeleton Gait Preference Landscapes" got accepted to the 2021 International Conference on Robotics and Automation (ICRA).
- Dec 23, 2020: Our paper titled "Incentivizing Routing Choices for Safe and Efficient Transportation in the Face of the COVID-19 Pandemic" got accepted to the 12th ACM/IEEE International Conference on Cyber-Physical Systems (ICCPS).
- Aug 12, 2020: Our paper titled "Multi-Agent Safe Planning with Gaussian Processes" got accepted to the 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).
- Jul 13, 2020: The recordings of our RSS 2020 workshop on "Emergent Behaviors in Human-Robot Systems" are available on YouTube.
- Jun 25, 2020: Check our IJRR submission about learning reward functions by optimally combining demonstration and preference data on arXiv.
- Jun 22, 2020: Our talks at RSS 2020 are available on YouTube now:
- Active Preference-Based Gaussian Process Regression for Reward Learning
- Reinforcement Learning based Control of Imitative Policies for Near-Accident Driving
- May 6, 2020: Our 2 papers got accepted to the Robotics: Science and Systems (RSS) 2020 conference:
- Active Preference-Based Gaussian Process Regression for Reward Learning
- Reinforcement Learning based Control of Imitative Policies for Near-Accident Driving
- Apr 7, 2020: Our paper titled "When Humans Aren't Optimal: Robots that Collaborate with Risk-Aware Humans" got honorable mention award at HRI 2020!
- Mar 28, 2020: Check Minae's talk at HRI 2020 on "When Humans Aren't Optimal: Robots that Collaborate with Risk-Aware Humans" here.
- Mar 6, 2020: We are organizing a workshop on "Emergent Behaviors in Human-Robot Systems" at RSS 2020. Check it out here for more details and the call for contributions.
- Dec 1, 2019: Our paper titled "When Humans Aren't Optimal: Robots that Collaborate with Risk-Aware Humans" got accepted to 2020 ACM/IEEE International Conference on Human-Robot Interaction (HRI).
- Oct 24, 2019: TechXplore compiled a story about our work "Asking Easy Questions: A User-Friendly Approach to Active Reward Learning". Check it out here.
- Sep 11, 2019: Our paper titled "Asking Easy Questions: A User-Friendly Approach to Active Reward Learning" got accepted to the Conference on Robot Learning (CoRL) 2019.
- Sep 10, 2019: Check our preprint about learning dynamic routing of autonomous cars to decrease traffic congestion on arXiv.
- Jul 19, 2019: Our paper titled "The Green Choice: Learning and Influencing Human Decisions on Shared Roads" got accepted at CDC 2019!
- Jul 18, 2019: Our paper titled "Active Learning of Reward Dynamics from Hierarchical Queries" got accepted to 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).
- Jun 19, 2019: Check our preprint about batch-mode active learning on arXiv.
- Apr 8, 2019: Check our CDC 2019 submission about mixed-autonomy traffic on arXiv.
- Jan 27, 2019: Our paper titled "Efficient and Safe Exploration in Deterministic Markov Decision Processes with Unknown Transition Models" got accepted at American Control Conference 2019.
- Sep 5, 2018: Our paper titled "Altruistic Autonomy: Beating Congestion on Shared Roads" got accepted to the 13th International Workshop on the Algorithmic Foundations of Robotics (WAFR).
- Sep 1, 2018: Our paper titled "Batch Active Preference-Based Learning of Reward Functions" got accepted at Conference on Robot Learning (CoRL) 2018.
|
