Publications

  • Connor Mattson, Jeremy C Clark & Daniel S Brown (2023). Exploring Behavior Discovery Methods for Heterogeneous Swarms of Limited- Capability Robots . IEEE International Symposium on Multi-Robot & Multi-Agent Systems (MRS). Published, 12/2023.
  • Jerry Zhi-Yang He, Daniel S Brown, Zackory Erickson & Anca Dragan (2023). Quantifying Assistive Robustness Via the Natural-Adversarial Frontier. Conference on Robot Learning (CoRL). Published, 12/2023.
  • Connor Mattson & Daniel S. Brown (2023). Leveraging Human Feedback to Evolve and Discover Novel Emergent Behaviors in Robot Swarms. Genetic and Evolutionary Computation Conference (GECCO). Published, 07/2023.
  • Gaurav Rohit Ghosal, Amrith Setlur, Daniel S Brown, Anca Dragan & Aditi Raghunathan (2023). Contextual Reliability: When Different Features Matter in Different Contexts. International Conference on Machine Learning (ICML). Published, 07/2023.
  • Jeremy Tien, Jerry Zhi-Yang He, Zackory Erickson, Anca D. Dragan & Daniel S. Brown (2023). Causal Confusion and Reward Misidentification in Preference-Based Reward Learning. International Conference on Learning Representations (ICLR). Published, 05/2023.
  • Yi Liu, Gaurav Datta, Ellen Novoseller & Daniel S. Brown (2023). Efficient Preference-Based Reinforcement Learning Using Learned Dynamics Models. International Conference on Robotics and Automation (ICRA). Published, 05/2023.
  • Andreea Bobu, Yi Liu, Rohin Shah, Daniel S. Brown & Anca D. Dragan (2023). SIRL: Similarity-based Implicit Representation Learning. ACM/IEEE International Conference on Human Robot Interaction (HRI). Published, 03/2023.
  • Gaurav R. Ghosal, Matthew Zurek, Daniel S. Brown & Anca D. Dragan (2023). The Effect of Modeling Human Rationality Level on Learning Rewards from Multiple Feedback Types. AAAI Conference on Artificial Intelligence (AAAI). Published, 02/2023.
  • Daniel Shin, Anca D. Dragan & Daniel S. Brown (2023). Benchmarks and Algorithms for Offline Preference-Based Reward Learning. Transactions on Machine Learning Research. Published, 01/2023.
  • Jerry Zhi-Yang He, Zackory Erickson, Daniel S. Brown, Aditi Raghunathan & Anca D. Dragan (2022). Learning Representations that Enable Generalization in Assistive Tasks. Conference on Robot Learning (CoRL). Published, 12/2022.
  • Albert Wilcox, Ashwin Balakrishna, Jules Dedieu, Wyame Benslimane, Daniel S. Brown & Ken Goldberg (2022). Monte Carlo Augmented Actor-Critic for Sparse Reward Deep Reinforcement Learning from Suboptimal Demonstrations. Neural Information Processing Systems (NeurIPS). Published, 12/2022.
  • Dimitris Papadimitriou, Usman Anwar & Daniel S. Brown (2022). Bayesian Methods for Constraint Inference in Reinforcement Learning. Transactions on Machine Learning Research. Published, 12/2022.
  • Arjun Sripathy, Andreea Bobu, Zhongyu Li, Koushil Sreenath, Daniel S. Brown & Anca D. Dragan (2022). Teaching Robots to Span the Space of Functional Expressive Motion. International Conference on Robot and Systems (IROS). Published, 10/2022.
  • Satvik Sharma, Ellen Novoseller, Vainavi Viswanath, Zaynah Javed, Rishi Parikh, Ryan Hoque, Ashwin Balakrishna, Daniel S. Brown & Ken Goldberg (2022). Learning Switching Criteria for Sim2Real Transfer of Robotic Fabric Manipulation Policies. IEEE International Conference on Automation Science and Engineering (CASE). Published, 08/2022.
  • Letian Fu, Michael DanielczukKen Goldberg , Ashwin Balakrishna, Daniel S. Brown, Jeffrey Ichnowski, Eugen Solowjow & Ken Goldberg (2022). LEGS: Learning Efficient Grasp Sets for Exploratory Grasping. International Conference on Robotics and Automation (ICRA). Published, 05/2022.
  • Ryan Hoque, Ashwin Balakrishna, Ellen Novoseller, Albert Wilcox, Daniel S. Brown & Ken Goldberg (2021). ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learning. Conference on Robot Learning (CoRL). Published, 11/2021.
  • Ryan Hoque, Ashwin Balakrishna, Carl Putterman, Michael Luo, Daniel S. Brown, Daniel Seita, Brijen Thananjeyan, Ellen Novoseller & Ken Goldberg (2021). LazyDAgger: Reducing Context Switching in Interactive Imitation Learning. IEEE Conference on Automation Science and Engineering (CASE). Published, 08/2021.

Presentations

  • Challenges and Progress Towards AI Alignment via Reinforcement Learning from Human Feedback. University of Utah Data Science Seminar. February, 2024. Invited Talk/Keynote, Presented, 02/2024.
  • Latent Spaces and Learned Representation for Better Human Preference Learning. CoRL 2022 Workshop on Aligning Robot Representations with Humans, Dec 2023. Invited Talk/Keynote, Presented, 12/2023.
  • Reinforcement Learning in and from the real-world. RL-CONFORM Workshop Panelist at the International Conference on Intelligent Robots and Systems (IROS). October, 2023. Invited Talk/Keynote, Presented, 10/2023.
  • Pitfalls and paths forward when learning rewards from human feedback. International Conference on Machine Learning (ICML) Workhop on Interactive learning with implicit human feedback. July, 2023. Invited Talk/Keynote, Presented, 07/2023.
  • Human-AI Alignment. Invited by Price College Engineering Deans office to present to Engineering National Advisory Council (ENAC). May, 2023. Invited Talk/Keynote, Presented, 05/2023.
  • Challenges and Progress Towards AI Alignment via Reinforcement Learning from Human Feedback. Marquette University Department Colloquium. March, 2023. Invited Talk/Keynote, Presented, 03/2023.
  • Challenges and Progress Towards Efficient and Causal Preference-Based Reward Learning. OpenAI Alignment Workshop, February, 2023. Invited Talk/Keynote, Presented, 02/2023.
  • Interactive Imitation Learning. University of Texas at Austin PeARL Lab. July, 2022. Invited Talk/Keynote, Presented, 07/2022.
  • Leveraging Human Input to Enable Robust AI Systems. Semiautonomous Seminar at UC Berkeley. July 2022. Invited Talk/Keynote, Presented, 07/2022.
  • Leveraging Human Input to Enable Robust AI Systems. Stanford Robotics Seminar. May, 2022. Invited Talk/Keynote, Presented, 05/2022.
  • Efficient and Robust Robot Learning of Human Objectives. University of Alberta Arti- ficial Intelligence Seminar. October, 2021. Invited Talk/Keynote, Presented, 10/2021.

Languages

  • Japanese, functional.