Anca D. Dragan

ORCID

Publication Activity (10 Years)

Years Active: 2011-2024
Publications (10 Years): 242

Top Venues

Publications

Micah Carroll, Davis Foote, Anand Siththaranjan, Stuart Russell, Anca D. Dragan
AI Alignment with Changing and Influenceable Reward Functions. CoRR (2024)
Evan Ellis, Gaurav R. Ghosal, Stuart J. Russell, Anca D. Dragan, Erdem Biyik
A Generalized Acquisition Function for Preference-based Reward Learning. CoRR (2024)
Jerry Zhi-Yang He, Sashrika Pandey, Mariah L. Schrum, Anca D. Dragan
CoS: Enhancing Personalization and Mitigating Bias with Context Steering. CoRR (2024)
Vivek Myers, Chongyi Zheng, Anca D. Dragan, Sergey Levine, Benjamin Eysenbach
Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making. CoRR (2024)
Marwa Abdulhai, Micah Carroll, Justin Svegliato, Anca D. Dragan, Sergey Levine
Defining Deception in Decision Making. AAMAS (2024)
Minae Kwon, Hengyuan Hu, Vivek Myers, Siddharth Karamcheti, Anca D. Dragan, Dorsa Sadigh
Toward Grounded Commonsense Reasoning. ICRA (2024)
Michelle Pan, Mariah Schrum, Vivek Myers, Erdem Biyik, Anca D. Dragan
Coprocessor Actor Critic: A Model-Based Reinforcement Learning Approach For Adaptive Brain Stimulation. CoRR (2024)
Cassidy Laidlaw, Banghua Zhu, Stuart Russell, Anca D. Dragan
The Effective Horizon Explains Deep RL Performance in Stochastic Environments. ICLR (2024)
Cassidy Laidlaw, Shivam Singhal, Anca D. Dragan
Preventing Reward Hacking with Occupancy Measure Regularization. CoRR (2024)
Evan Ellis, Gaurav R. Ghosal, Stuart J. Russell, Anca D. Dragan, Erdem Biyik
A Generalized Acquisition Function for Preference-based Reward Learning. ICRA (2024)
Ted Moskovitz, Aaditya K. Singh, DJ Strouse, Tuomas Sandholm, Ruslan Salakhutdinov, Anca D. Dragan, Stephen Marcus McAleer
Confronting Reward Model Overoptimization with Constrained RLHF. ICLR (2024)
W. Bradley Knox, Stephane Hatgis-Kessell, Sigurdur O. Adalgeirsson, Serena Booth, Anca D. Dragan, Peter Stone, Scott Niekum
Learning Optimal Advantage from Preferences and Mistaking It for Reward. AAAI (2024)
Mary Phuong, Matthew Aitchison, Elliot Catt, Sarah Cogan, Alexandre Kaskasoli, Victoria Krakovna, David Lindner, Matthew Rahtz, Yannis Assael, Sarah Hodkinson, Heidi Howard, Tom Lieberum, Ramana Kumar, Maria Abi Raad, Albert Webson, Lewis Ho, Sharon Lin, Sebastian Farquhar, Marcus Hutter, Grégoire Delétang, Anian Ruoss, Seliem El-Sayed, Sasha Brown, Anca D. Dragan, Rohin Shah, Allan Dafoe, Toby Shevlane
Evaluating Frontier Models for Dangerous Capabilities. CoRR (2024)
Erik Jones, Anca D. Dragan, Jacob Steinhardt
Adversaries Can Misuse Combinations of Safe Models. CoRR (2024)
Joey Hong, Anca D. Dragan, Sergey Levine
Offline RL with Observation Histories: Analyzing and Improving Sample Complexity. ICLR (2024)
Andreea Bobu, Andi Peng, Pulkit Agrawal, Julie A. Shah, Anca D. Dragan
Aligning Human and Robot Representations. HRI (2024)
Leon Lang, Davis Foote, Stuart Russell, Anca D. Dragan, Erik Jenner, Scott Emmons
When Your AIs Deceive You: Challenges with Partial Observability of Human Evaluators in Reward Learning. CoRR (2024)
Vivek Myers, Andre He, Kuan Fang, Homer Walke, Philippe Hansen-Estruch, Ching-An Cheng, Mihai Jalobeanu, Andrey Kolobov, Anca D. Dragan, Sergey Levine
Goal Representations for Instruction Following: A Semi-Supervised Language Interface to Control. CoRR (2023)
Joey Hong, Kush Bhatia, Anca D. Dragan
On the Sensitivity of Reward Inference to Misspecified Human Models. ICLR (2023)
Daniel Shin, Anca D. Dragan, Daniel S. Brown
Benchmarks and Algorithms for Offline Preference-Based Reward Learning. CoRR (2023)
W. Bradley Knox, Stephane Hatgis-Kessell, Sigurdur O. Adalgeirsson, Serena Booth, Anca D. Dragan, Peter Stone, Scott Niekum
Learning Optimal Advantage from Preferences and Mistaking it for Reward. CoRR (2023)
Joey Hong, Anca D. Dragan, Sergey Levine
Offline RL with Observation Histories: Analyzing and Improving Sample Complexity. CoRR (2023)
Ran Tian, Masayoshi Tomizuka, Anca D. Dragan, Andrea Bajcsy
Towards Modeling and Influencing the Dynamics of Human Learning. HRI (2023)
Gaurav R. Ghosal, Matthew Zurek, Daniel S. Brown, Anca D. Dragan
The Effect of Modeling Human Rationality Level on Learning Rewards from Multiple Feedback Types. AAAI (2023)
Jensen Gao, Siddharth Reddy, Glen Berseth, Anca D. Dragan, Sergey Levine
Bootstrapping Adaptive Human-Machine Interfaces with Offline Reinforcement Learning. CoRR (2023)
Jensen Gao, Siddharth Reddy, Glen Berseth, Anca D. Dragan, Sergey Levine
Bootstrapping Adaptive Human-Machine Interfaces with Offline Reinforcement Learning. IROS (2023)
Smitha Milli, Micah Carroll, Sashrika Pandey, Yike Wang, Anca D. Dragan
Twitter's Algorithm: Amplifying Anger, Animosity, and Affective Polarization. CoRR (2023)
Ted Moskovitz, Aaditya K. Singh, DJ Strouse, Tuomas Sandholm, Ruslan Salakhutdinov, Anca D. Dragan, Stephen McAleer
Confronting Reward Model Overoptimization with Constrained RLHF. CoRR (2023)
Stephen Casper, Xander Davies, Claudia Shi, Thomas Krendl Gilbert, Jérémy Scheurer, Javier Rando, Rachel Freedman, Tomasz Korbak, David Lindner, Pedro Freire, Tony Tong Wang, Samuel Marks, Charbel-Raphaël Ségerie, Micah Carroll, Andi Peng, Phillip J. K. Christoffersen, Mehul Damani, Stewart Slocum, Usman Anwar, Anand Siththaranjan, Max Nadeau, Eric J. Michaud, Jacob Pfau, Dmitrii Krasheninnikov, Xin Chen, Lauro Langosco, Peter Hase, Erdem Biyik, Anca D. Dragan, David Krueger, Dorsa Sadigh, Dylan Hadfield-Menell
Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback. Trans. Mach. Learn. Res. 2023 (2023)
Andreea Bobu, Yi Liu, Rohin Shah, Daniel S. Brown, Anca D. Dragan
SIRL: Similarity-based Implicit Representation Learning. CoRR (2023)
Jessy Lin, Yuqing Du, Olivia Watkins, Danijar Hafner, Pieter Abbeel, Dan Klein, Anca D. Dragan
Learning to Model the World with Language. CoRR (2023)
Yoshua Bengio, Geoffrey E. Hinton, Andrew Yao, Dawn Song, Pieter Abbeel, Yuval Noah Harari, Ya-Qin Zhang, Lan Xue, Shai Shalev-Shwartz, Gillian K. Hadfield, Jeff Clune, Tegan Maharaj, Frank Hutter, Atilim Günes Baydin, Sheila McIlraith, Qiqi Gao, Ashwin Acharya, David Krueger, Anca D. Dragan, Philip H. S. Torr, Stuart Russell, Daniel Kahneman, Jan Brauner, Sören Mindermann
Managing AI Risks in an Era of Rapid Progress. CoRR (2023)
Jerry Zhi-Yang He, Daniel S. Brown, Zackory Erickson, Anca D. Dragan
Quantifying Assistive Robustness Via the Natural-Adversarial Frontier. CoRL (2023)
Stephen Casper, Xander Davies, Claudia Shi, Thomas Krendl Gilbert, Jérémy Scheurer, Javier Rando, Rachel Freedman, Tomasz Korbak, David Lindner, Pedro Freire, Tony Wang, Samuel Marks, Charbel-Raphaël Ségerie, Micah Carroll, Andi Peng, Phillip J. K. Christoffersen, Mehul Damani, Stewart Slocum, Usman Anwar, Anand Siththaranjan, Max Nadeau, Eric J. Michaud, Jacob Pfau, Dmitrii Krasheninnikov, Xin Chen, Lauro Langosco, Peter Hase, Erdem Biyik, Anca D. Dragan, David Krueger, Dorsa Sadigh, Dylan Hadfield-Menell
Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback. CoRR (2023)
Vivek Myers, Andre Wang He, Kuan Fang, Homer Rich Walke, Philippe Hansen-Estruch, Ching-An Cheng, Mihai Jalobeanu, Andrey Kolobov, Anca D. Dragan, Sergey Levine
Goal Representations for Instruction Following: A Semi-Supervised Language Interface to Control. CoRL (2023)
Gaurav Rohit Ghosal, Amrith Setlur, Daniel S. Brown, Anca D. Dragan, Aditi Raghunathan
Contextual Reliability: When Different Features Matter in Different Contexts. ICML (2023)
Joey Hong, Sergey Levine, Anca D. Dragan
Zero-Shot Goal-Directed Dialogue via RL on Imagined Conversations. CoRR (2023)
Andreea Bobu, Andi Peng, Pulkit Agrawal, Julie Shah, Anca D. Dragan
Aligning Robot and Human Representations. CoRR (2023)
Joey Hong, Anca D. Dragan, Sergey Levine
Learning to Influence Human Behavior with Offline Reinforcement Learning. CoRR (2023)
Daniel Shin, Anca D. Dragan, Daniel S. Brown
Benchmarks and Algorithms for Offline Preference-Based Reward Learning. Trans. Mach. Learn. Res. 2023 (2023)
Jeremy Tien, Jerry Zhi-Yang He, Zackory Erickson, Anca D. Dragan, Daniel S. Brown
Causal Confusion and Reward Misidentification in Preference-Based Reward Learning. ICLR (2023)
Andreea Bobu, Yi Liu, Rohin Shah, Daniel S. Brown, Anca D. Dragan
SIRL: Similarity-based Implicit Representation Learning. HRI (2023)
Joey Hong, Sergey Levine, Anca D. Dragan
Learning to Influence Human Behavior with Offline Reinforcement Learning. NeurIPS (2023)
Erik Jones, Anca D. Dragan, Aditi Raghunathan, Jacob Steinhardt
Automatically Auditing Large Language Models via Discrete Optimization. ICML (2023)
Cassidy Laidlaw, Banghua Zhu, Stuart Russell, Anca D. Dragan
The Effective Horizon Explains Deep RL Performance in Stochastic Environments. CoRR (2023)
Cassidy Laidlaw, Stuart J. Russell, Anca D. Dragan
Bridging RL Theory and Practice with the Effective Horizon. NeurIPS (2023)
Minae Kwon, Hengyuan Hu, Vivek Myers, Siddharth Karamcheti, Anca D. Dragan, Dorsa Sadigh
Toward Grounded Social Reasoning. CoRR (2023)
Jerry Zhi-Yang He, Zackory Erickson, Daniel S. Brown, Anca D. Dragan
Quantifying Assistive Robustness Via the Natural-Adversarial Frontier. CoRR (2023)
Cassidy Laidlaw, Stuart Russell, Anca D. Dragan
Bridging RL Theory and Practice with the Effective Horizon. CoRR (2023)
Ran Tian, Masayoshi Tomizuka, Anca D. Dragan, Andrea Bajcsy
Towards Modeling and Influencing the Dynamics of Human Learning. CoRR (2023)
Erik Jones, Anca D. Dragan, Aditi Raghunathan, Jacob Steinhardt
Automatically Auditing Large Language Models via Discrete Optimization. CoRR (2023)
Gaurav R. Ghosal, Amrith Setlur, Daniel S. Brown, Anca D. Dragan, Aditi Raghunathan
Contextual Reliability: When Different Features Matter in Different Contexts. CoRR (2023)
Micah D. Carroll, Anca D. Dragan, Stuart Russell, Dylan Hadfield-Menell
Estimating and Penalizing Induced Preference Shifts in Recommender Systems. ICML (2022)
Jensen Gao, Siddharth Reddy, Glen Berseth, Anca D. Dragan, Sergey Levine
X2T: Training an X-to-Text Typing Interface with Online Learning from User Feedback. CoRR (2022)
Micah Carroll, Jessy Lin, Orr Paradise, Raluca Georgescu, Mingfei Sun, David Bignell, Stephanie Milani, Katja Hofmann, Matthew Hausknecht, Anca D. Dragan, Sam Devlin
Towards Flexible Inference in Sequential Decision Problems via Bidirectional Transformers. CoRR (2022)
Micah Carroll, Orr Paradise, Jessy Lin, Raluca Georgescu, Mingfei Sun, David Bignell, Stephanie Milani, Katja Hofmann, Matthew Hausknecht, Anca D. Dragan, Sam Devlin
UniMASK: Unified Inference in Sequential Decision Problems. CoRR (2022)
Ran Tian, Liting Sun, Andrea Bajcsy, Masayoshi Tomizuka, Anca D. Dragan
Safety Assurances for Human-Robot Interaction via Confidence-aware Game-theoretic Human Models. ICRA (2022)
Micah Carroll, Dylan Hadfield-Menell, Stuart Russell, Anca D. Dragan
Estimating and Penalizing Induced Preference Shifts in Recommender Systems. CoRR (2022)
Jerry Zhi-Yang He, Aditi Raghunathan, Daniel S. Brown, Zackory Erickson, Anca D. Dragan
Learning Representations that Enable Generalization in Assistive Tasks. CoRR (2022)
Arjun Sripathy, Andreea Bobu, Zhongyu Li, Koushil Sreenath, Daniel S. Brown, Anca D. Dragan
Teaching Robots to Span the Space of Functional Expressive Motion. IROS (2022)
Andreea Bobu, Marius Wiggert, Claire J. Tomlin, Anca D. Dragan
Inducing structure in reward learning by learning features. Int. J. Robotics Res. 41 (5) (2022)
Dylan P. Losey, Andrea Bajcsy, Marcia K. O'Malley, Anca D. Dragan
Physical interaction as communication: Learning robot objectives online from human corrections. Int. J. Robotics Res. 41 (1) (2022)
Sean Chen, Jensen Gao, Siddharth Reddy, Glen Berseth, Anca D. Dragan, Sergey Levine
ASHA: Assistive Teleoperation via Human-in-the-Loop Reinforcement Learning. ICRA (2022)
Siddharth Reddy, Sergey Levine, Anca D. Dragan
First Contact: Unsupervised Human-Machine Co-Adaptation via Mutual Information Maximization. NeurIPS (2022)
Joey Hong, Kush Bhatia, Anca D. Dragan
On the Sensitivity of Reward Inference to Misspecified Human Models. CoRR (2022)
Gaurav R. Ghosal, Matthew Zurek, Daniel S. Brown, Anca D. Dragan
The Effect of Modeling Human Rationality Level on Learning Rewards from Multiple Feedback Types. CoRR (2022)
Cassidy Laidlaw, Anca D. Dragan
The Boltzmann Policy Distribution: Accounting for Systematic Suboptimality in Human Models. CoRR (2022)
Cassidy Laidlaw, Anca D. Dragan
The Boltzmann Policy Distribution: Accounting for Systematic Suboptimality in Human Models. ICLR (2022)
Mesut Yang, Micah Carroll, Anca D. Dragan
Optimal Behavior Prior: Data-Efficient Human Models for Improved Human-AI Collaboration. CoRR (2022)
Siddharth Reddy, Sergey Levine, Anca D. Dragan
First Contact: Unsupervised Human-Machine Co-Adaptation via Mutual Information Maximization. CoRR (2022)
Jessy Lin, Daniel Fried, Dan Klein, Anca D. Dragan
Inferring Rewards from Language in Context. CoRR (2022)
Micah Carroll, Orr Paradise, Jessy Lin, Raluca Georgescu, Mingfei Sun, David Bignell, Stephanie Milani, Katja Hofmann, Matthew J. Hausknecht, Anca D. Dragan, Sam Devlin
Uni[MASK]: Unified Inference in Sequential Decision Problems. NeurIPS (2022)
Arjun Sripathy, Andreea Bobu, Zhongyu Li, Koushil Sreenath, Daniel S. Brown, Anca D. Dragan
Teaching Robots to Span the Space of Functional Expressive Motion. CoRR (2022)
David Zhang, Micah Carroll, Andreea Bobu, Anca D. Dragan
Time-Efficient Reward Learning via Visually Assisted Cluster Ranking. CoRR (2022)
Jeremy Tien, Jerry Zhi-Yang He, Zackory Erickson, Anca D. Dragan, Daniel S. Brown
A Study of Causal Confusion in Preference-Based Reward Learning. CoRR (2022)
Sean Chen, Jensen Gao, Siddharth Reddy, Glen Berseth, Anca D. Dragan, Sergey Levine
ASHA: Assistive Teleoperation via Human-in-the-Loop Reinforcement Learning. CoRR (2022)
Andreea Bobu, Marius Wiggert, Claire J. Tomlin, Anca D. Dragan
Inducing Structure in Reward Learning by Learning Features. CoRR (2022)
Jessy Lin, Daniel Fried, Dan Klein, Anca D. Dragan
Inferring Rewards from Language in Context. ACL (1) (2022)
Jerry Zhi-Yang He, Zackory Erickson, Daniel S. Brown, Aditi Raghunathan, Anca D. Dragan
Learning Representations that Enable Generalization in Assistive Tasks. CoRL (2022)
Siddharth Reddy, Anca D. Dragan, Sergey Levine
Pragmatic Image Compression for Human-in-the-Loop Decision-Making. CoRR (2021)
Andreea Bobu, Marius Wiggert, Claire J. Tomlin, Anca D. Dragan
Feature Expansive Reward Learning: Rethinking Human Input. HRI (2021)
Kimin Lee, Laura M. Smith, Anca D. Dragan, Pieter Abbeel
B-Pref: Benchmarking Preference-Based Reinforcement Learning. NeurIPS Datasets and Benchmarks (2021)
Andrea Bajcsy, Somil Bansal, Ellis Ratner, Claire J. Tomlin, Anca D. Dragan
A Robust Control Framework for Human Motion Prediction. IEEE Robotics Autom. Lett. 6 (1) (2021)
Zaynah Javed, Daniel S. Brown, Satvik Sharma, Jerry Zhu, Ashwin Balakrishna, Marek Petrik, Anca D. Dragan, Ken Goldberg
Policy Gradient Bayesian Robust Optimization for Imitation Learning. CoRR (2021)
Arjun Sripathy, Andreea Bobu, Daniel S. Brown, Anca D. Dragan
Dynamically Switching Human Prediction Models for Efficient Planning. ICRA (2021)
Andrea Bajcsy, Anand Siththaranjan, Claire J. Tomlin, Anca D. Dragan
Analyzing Human Models that Adapt Online. CoRR (2021)
Jensen Gao, Siddharth Reddy, Glen Berseth, Nicholas Hardy, Nikhilesh Natraj, Karunesh Ganguly, Anca D. Dragan, Sergey Levine
X2T: Training an X-to-Text Typing Interface with Online Learning from User Feedback. ICLR (2021)
Daniel S. Brown, Jordan Schneider, Anca D. Dragan, Scott Niekum
Value Alignment Verification. ICML (2021)
Kush Bhatia, Ashwin Pananjady, Peter L. Bartlett, Anca D. Dragan, Martin J. Wainwright
Preference learning along multiple criteria: A game-theoretic perspective. CoRR (2021)
Zaynah Javed, Daniel S. Brown, Satvik Sharma, Jerry Zhu, Ashwin Balakrishna, Marek Petrik, Anca D. Dragan, Ken Goldberg
Policy Gradient Bayesian Robust Optimization for Imitation Learning. ICML (2021)
Lawrence Chan, Andrew Critch, Anca D. Dragan
Human irrationality: both bad and good for reward inference. CoRR (2021)
Paul Knott, Micah Carroll, Sam Devlin, Kamil Ciosek, Katja Hofmann, Anca D. Dragan, Rohin Shah
Evaluating the Robustness of Collaborative Agents. AAMAS (2021)
Kush Bhatia, Peter L. Bartlett, Anca D. Dragan, Jacob Steinhardt
Agnostic learning with unknown utilities. CoRR (2021)
Rachel Freedman, Rohin Shah, Anca D. Dragan
Choice Set Misspecification in Reward Inference. CoRR (2021)
Avik Jain, Lawrence Chan, Daniel S. Brown, Anca D. Dragan
Optimal Cost Design for Model Predictive Control. L4DC (2021)
Kush Bhatia, Peter L. Bartlett, Anca D. Dragan, Jacob Steinhardt
Agnostic Learning with Unknown Utilities. ITCS (2021)
Matthew Zurek, Andreea Bobu, Daniel S. Brown, Anca D. Dragan
Situational Confidence Assistance for Lifelong Shared Autonomy. CoRR (2021)
Ran Tian, Liting Sun, Andrea Bajcsy, Masayoshi Tomizuka, Anca D. Dragan
Safety Assurances for Human-Robot Interaction via Confidence-aware Game-theoretic Human Models. CoRR (2021)
Rohin Shah, Cody Wild, Steven H. Wang, Neel Alex, Brandon Houghton, William H. Guss, Sharada P. Mohanty, Anssi Kanervisto, Stephanie Milani, Nicholay Topin, Pieter Abbeel, Stuart Russell, Anca D. Dragan
The MineRL BASALT Competition on Learning from Human Feedback. CoRR (2021)
Sid Reddy, Anca D. Dragan, Sergey Levine
Pragmatic Image Compression for Human-in-the-Loop Decision-Making. NeurIPS (2021)

Anca D. Dragan.css-eqlu8i{font-size:small;padding-left:4px;}

Publication Activity (10 Years)

Top Topics

Top Venues

Anca D. Dragan