Publications

DynaMITE-RL: A Dynamic Model for Improved Temporal Meta-Reinforcement Learning Anthony Liang, Guy Tennenholtz, Chih-wei Hsu, Yinlam Chow, Erdem Bıyık, Craig Boutilier Conference on Neural Information Processing Systems (NeurIPS), December 2024
Trajectory Improvement and Reward Learning from Comparative Language Feedback Zhaojing Yang, Miru Jun, Jeremy Tien, Stuart J. Russell, Anca Dragan, Erdem Bıyık Proceedings of the 8th Conference on Robot Learning (CoRL), November 2024 Also presented at HRI Human-Interactive Robot Learning Workshop, March 2024 (PDF).
EXTRACT: Efficient Policy Learning by Extracting Transferable Robot Skills from Offline Data Jesse Zhang, Minho Heo, Zuxin Liu, Erdem Bıyık, Joseph J Lim, Yao Liu, Rasool Fakoor Proceedings of the 8th Conference on Robot Learning (CoRL), November 2024
Accurate and Data-Efficient Toxicity Prediction when Annotators Disagree Harbani Jaggi, Kashyap Murali, Eve Fleisig, Erdem Bıyık Conference on Empirical Methods in Natural Language Processing (EMNLP), November 2024 * denotes equal contribution.
ViSaRL: Visual Reinforcement Learning Guided by Human Saliency Anthony Liang, Jesse Thomason, Erdem Bıyık International Conference on Intelligent Robots and Systems (IROS), October 2024 Also presented at ICRA Pretraining for Robotics Workshop, May 2023 (PDF).
Mitigating Suboptimality of Deterministic Policy Gradients in Complex Q-functions Ayush Jain, Norio Kosaka, Xinhu Li, Kyung-Min Kim, Erdem Bıyık, Joseph J. Lim arXiv preprint, October 2024
RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedback Yufei Wang, Zhanyi Sun, Jesse Zhang, Zhou Xian, Erdem Bıyık, David Held†, Zackory Erickson† International Conference on Machine Learning (ICML), July 2024 * denotes equal contribution. † denotes equal advising.
Coprocessor Actor Critic: A Model-Based Reinforcement Learning Approach For Adaptive Brain Stimulation Michelle Pan, Mariah Schrum, Vivek Myers, Erdem Bıyık, Anca Dragan International Conference on Machine Learning (ICML), July 2024 * denotes equal contribution.
Foundation Models for Embodied AI Sumedh Anand Sontakke CS Department, University of Southern California, May 2024 Ph.D. Dissertation
Batch Active Learning of Reward Functions from Human Preferences Erdem Bıyık, Nima Anari, Dorsa Sadigh ACM Transactions on Human-Robot Interaction (THRI), 2024
A Generalized Acquisition Function for Preference-based Reward Learning Evan Ellis, Gaurav R. Ghosal, Stuart J. Russell, Anca Dragan, Erdem Bıyık International Conference on Robotics and Automation (ICRA), May 2024
Active Preference-Based Gaussian Process Regression for Reward Learning and Optimization Erdem Bıyık, Nicolas Huynh, Mykel J. Kochenderfer, Dorsa Sadigh International Journal of Robotics Research (IJRR), 2024
Preference Elicitation with Soft Attributes in Interactive Recommendation Erdem Bıyık, Fan Yao, Yinlam Chow, Alex Haig, Chih-wei Hsu, Mohammad Ghavamzadeh, Craig Boutilier arXiv preprint, November 2023
RoboCLIP: One Demonstration is Enough to Learn Robot Policies Sumedh A. Sontakke, Jesse Zhang, Sébastien M. R. Arnold, Karl Pertsch, Erdem Bıyık, Dorsa Sadigh, Chelsea Finn, Laurent Itti Conference on Neural Information Processing Systems (NeurIPS), December 2023
Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback Stephen Casper, Xander Davies, et al. Transactions on Machine Learning Research (TMLR), 2023 * denotes equal contribution.
Active Reward Learning from Online Preferences Vivek Myers, Erdem Bıyık, Dorsa Sadigh International Conference on Robotics and Automation (ICRA), May 2023
Assistive Teaching of Motor Control Tasks to Humans Megha Srivastava, Erdem Bıyık, Suvir Mirchandani, Noah Goodman, Dorsa Sadigh Conference on Neural Information Processing Systems (NeurIPS), November 2022
How do People Incorporate Advice from Artificial Agents when Making Physical Judgments? Erik Brockbank, Haoliang Wang, Justin Yang, Suvir Mirchandani, Erdem Bıyık, Dorsa Sadigh, Judith Fan Cognitive Science Society Conference (CogSci), July 2022 * denotes equal contribution. Oral presentation.
Learning Preferences For Interactive Autonomy Erdem Bıyık EE Department, Stanford University, May 2022 Ph.D. Dissertation
Leveraging Smooth Attention Prior for Multi-Agent Trajectory Prediction Zhangjie Cao, Erdem Bıyık, Guy Rosman, Dorsa Sadigh International Conference on Robotics and Automation (ICRA), May 2022
APReL: A Library for Active Preference-based Reward Learning Algorithms Erdem Bıyık, Aditi Talati, Dorsa Sadigh 17th ACM/IEEE International Conference on Human-Robot Interaction (HRI), March 2022 Also presented at Artificial Intelligence for Human-Robot Interaction (AI-HRI) at AAAI Fall Symposium Series, November 2021 (PDF).
Learning from Humans for Adaptive Interaction Erdem Bıyık The 17th Annual Human-Robot Interaction Pioneers Workshop (HRI Pioneers), March 2022
Partner-Aware Algorithms in Decentralized Cooperative Bandit Teams Erdem Bıyık, Anusha Lalitha, Rajarshi Saha, Andrea Goldsmith, Dorsa Sadigh Proceedings of the 36th AAAI Conference on Artificial Intelligence, February 2022 Also presented at Artificial Intelligence for Human-Robot Interaction (AI-HRI) at AAAI Fall Symposium Series, November 2021 (PDF). Oral presentation.
Learning Multimodal Rewards from Rankings Vivek Myers, Erdem Bıyık, Nima Anari, Dorsa Sadigh Proceedings of the 5th Conference on Robot Learning (CoRL), November 2021 Oral presentation.
Learning Reward Functions from Scale Feedback Nils Wilde, Erdem Bıyık, Dorsa Sadigh, Stephen L. Smith Proceedings of the 5th Conference on Robot Learning (CoRL), November 2021 * denotes equal contribution.
Learning Reward Functions from Diverse Sources of Human Feedback: Optimally Integrating Demonstrations and Preferences Erdem Bıyık, Dylan P. Losey, Malayandi Palan, Nicholas C. Landolfi, Gleb Shevchuk, Dorsa Sadigh The International Journal of Robotics Research (IJRR), 2021
Learning How to Dynamically Route Autonomous Vehicles on Shared Roads Daniel A. Lazar, Erdem Bıyık, Dorsa Sadigh, Ramtin Pedarsani Transportation Research Part C: Emerging Technologies (TR_C), September 2021 * denotes equal contribution.
Emergent Prosociality in Multi-Agent Games Through Gifting Woodrow Z. Wang, Mark Beliaev, Erdem Bıyık, Daniel A. Lazar, Ramtin Pedarsani, Dorsa Sadigh 30th International Joint Conference on Artificial Intelligence (IJCAI), August 2021* * denotes equal contribution.
Incentivizing Efficient Equilibria in Traffic Networks with Mixed Autonomy Erdem Bıyık, Daniel A. Lazar, Ramtin Pedarsani, Dorsa Sadigh IEEE Transactions on Control of Network Systems (TCNS), 2021 * denotes equal contribution.
ROIAL: Region of Interest Active Learning for Characterizing Exoskeleton Gait Preference Landscapes Kejun Li, Maegan Tucker, Erdem Bıyık, Ellen Novoseller, Joel W. Burdick, Yanan Sui, Dorsa Sadigh, Yisong Yue, Aaron D. Ames International Conference on Robotics and Automation (ICRA), May 2021
Incentivizing Routing Choices for Safe and Efficient Transportation in the Face of the COVID-19 Pandemic Mark Beliaev, Erdem Bıyık, Daniel A. Lazar, Woodrow Z. Wang, Dorsa Sadigh, Ramtin Pedarsani 12th ACM/IEEE International Conference on Cyber-Physical Systems (ICCPS), May 2021
Multi-Agent Safe Planning with Gaussian Processes Zheqing Zhu, Erdem Bıyık, Dorsa Sadigh Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), October 2020
Active Preference-Based Gaussian Process Regression for Reward Learning Erdem Bıyık, Nicolas Huynh, Mykel J. Kochenderfer, Dorsa Sadigh Proceedings of Robotics: Science and Systems (RSS), July 2020 * denotes equal contribution.
Reinforcement Learning based Control of Imitative Policies for Near-Accident Driving Zhangjie Cao, Erdem Bıyık, Woodrow Z. Wang, Allan Raventos, Adrien Gaidon, Guy Rosman, Dorsa Sadigh Proceedings of Robotics: Science and Systems (RSS), July 2020 * denotes equal contribution.
Emergent Correlated Equilibrium through Synchronized Exploration Mark Beliaev, Woodrow Z. Wang, Daniel A. Lazar, Erdem Bıyık, Dorsa Sadigh, Ramtin Pedarsani RSS 2020 Workshop on Emergent Behaviors in Human-Robot Systems, July 2020
When Humans Aren't Optimal: Robots that Collaborate with Risk-Aware Humans Minae Kwon, Erdem Bıyık, Aditi Talati, Karan Bhasin, Dylan P. Losey, Dorsa Sadigh ACM/IEEE International Conference on Human-Robot Interaction (HRI), March 2020 Also presented at Cooperative AI NeurIPS Workshop 2021, December 2021 (PDF). Honorable mention award.
The Green Choice: Learning and Influencing Human Decisions on Shared Roads Erdem Bıyık, Daniel A. Lazar, Dorsa Sadigh, Ramtin Pedarsani Proceedings of the 58th IEEE Conference on Decision and Control (CDC), December 2019
Active Learning of Reward Dynamics from Hierarchical Queries Chandrayee Basu, Erdem Bıyık, Zhixun He, Mukesh Singhal, Dorsa Sadigh Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), November 2019
Asking Easy Questions: A User-Friendly Approach to Active Reward Learning Erdem Bıyık, Malayandi Palan, Nicholas C. Landolfi, Dylan P. Losey, Dorsa Sadigh Proceedings of the 3rd Conference on Robot Learning (CoRL), October 2019
Efficient and Safe Exploration in Deterministic Markov Decision Processes with Unknown Transition Models Erdem Bıyık, Jonathan Margoliash, Shahrouz R. Alimo, Dorsa Sadigh Proceedings of the American Control Conference (ACC), July 2019 * denotes equal contribution.
Batch Active Learning Using Determinantal Point Processes Erdem Bıyık, Kenneth Wang, Nima Anari, Dorsa Sadigh arXiv preprint, June 2019
Altruistic Autonomy: Beating Congestion on Shared Roads Erdem Bıyık, Daniel A. Lazar, Ramtin Pedarsani, Dorsa Sadigh Proceedings of the 13th International Workshop on Algorithmic Foundations of Robotics (WAFR), December 2018 * denotes equal contribution.
Batch Active Preference-Based Learning of Reward Functions Erdem Bıyık, Dorsa Sadigh Proceedings of the 2nd Conference on Robot Learning (CoRL), October 2018 Oral presentation.
Real-Time Detection, Tracking and Classification of Multiple Moving Objects in UAV Videos Hüseyin C. Baykara, Erdem Bıyık, Gamze Gül, Deniz Onural, Ahmet S. Öztürk, İlkay Yıldız International Conference on Tools with Artificial Intelligence (ICTAI), November 2017 * denotes equal contribution.