Scholar
Bradly Stadie
Google Scholar ID: lEV5F5kAAAAJ
Assistant Professor, Northwestern
Citations & Impact
Citations
2,117
H-index
13
i10-index
15
Publications
20
Co-authors
8
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Publications:
- - D2 Actor Critic: Diffusion Actor Meets Distributional Critic (TMLR, 2025)
- - LAMP: Extracting Locally Linear Decision Surfaces from LLM World Models (arXiv preprint, 2025)
- - Of Mice and Machines: A Comparison of Learning Between Real World Mice and RL Agents (ICML, 2025)
- - Thoughts and Lessons on Using Visual Foundation Models for Manipulation (TMLR, 2025)
- - Solving Robotics Problems in Zero-Shot with Vision-Language Models (TMLR, 2024)
- - Artificial Intelligence Safety in Evidence-Based Medicine via Expert-of-Experts Verification and Alignment (EVAL) with Application to Upper Gastrointestinal Bleeding (Nature Digital Medicine, 2024)
- - Cold Diffusion on the Replay Buffer: Learning to Plan from Known Good States (CoRL, 2023)
- - To the Noise and Back: Diffusion for Shared Autonomy (RSS, 2023)
- - Understanding Goal Relabeling Requires Rethinking Divergence Minimization (NeurIPS Deep RL workshop, 2022)
- - Invariance Through Inference (RSS, 2022)
- - World Model as a Graph: Learning Latent Landmarks for Planning (ICML, 2021)
- - Maximum Entropy Gain Exploration for Long Horizon Multi-goal Reinforcement Learning (ICML, 2020)
- - Learning Intrinsic Rewards as a Bi-Level Optimization Problem (Conference on Uncertainty in Artificial Intelligence, 2021)
Research Experience
- - Assistant Professor, Northwestern University Department of Statistics and Data Science
- - Research Assistant Professor, Toyota Technological Institute at Chicago (TTIC), located on the campus of the University of Chicago
- - Research Scientist, Open AI
Education
- - Ph.D., University of California, Berkeley, Advisor: Pieter Abbeel
- - Research Scientist, Open AI, Advisor: Ilya Sutskever
- - B.A. in Mathematics, University of Chicago, Advisor: Paul Sally
Background
- Research Interests: Developing machine intelligence, particularly reinforcement learning and planning. Research areas include planning in robotics, goal-conditioned reinforcement learning, diffusion for shared autonomy, planning in animals, and causal inference. Recent research focuses on the intersection of large language models (LLMs) and physical task planning.
Miscellany
- Made a YouTube video about some of his research for a general audience.
