Michael Janner

Michael Janner I am a researcher at OpenAI, where I work on large-scale languaging modeling, reinforcement learning, and ChatGPT. I received my PhD from UC Berkeley, where I was advised by Sergey Levine. Before that, I was an undergrad at MIT, where I worked with Josh Tenenbaum, Regina Barzilay, and Bill Freeman. [janner [at] berkeley (dot) edu] [github] [google scholar] Selected Publications
Training Diffusion Models with Reinforcement Learning Kevin Black, Michael Janner, Yilun Du, Ilya Kostrikov, Sergey Levine arXiv 2023 [arxiv] [project page] [code]	pretrained
Planning with Diffusion for Flexible Behavior Synthesis Michael Janner, Yilun Du, Joshua Tenenbaum, Sergey Levine ICML 2022 (long talk) [arxiv] [project page] [code]
Offline Reinforcement Learning as One Big Sequence Modeling Problem Michael Janner, Qiyang Li, Sergey Levine NeurIPS 2021 (spotlight) [arxiv] [project page] [code]
Generative Temporal Difference Learning for Infinite-Horizon Prediction Michael Janner, Igor Mordatch, Sergey Levine NeurIPS 2020 [arxiv] [project page] [code]
When to Trust Your Model: Model-Based Policy Optimization Michael Janner, Justin Fu, Marvin Zhang, Sergey Levine NeurIPS 2019 [arxiv] [project page] [code]
Reasoning About Physical Interactions with Object-Oriented Prediction and Planning Michael Janner, Sergey Levine, William Freeman, Joshua Tenenbaum, Chelsea Finn, Jiajun Wu ICLR 2019 [arxiv] [project page] [code]
Representation Learning for Grounded Spatial Reasoning Michael Janner, Karthik Narasimhan, Regina Barzilay TACL 2018 [arxiv] [code]
Self-Supervised Intrinsic Image Decomposition Michael Janner, Jiajun Wu, Tejas Kulkarni, Ilker Yildirim, Joshua Tenenbaum Best Paper at New England Computer Vision Workshop 2017 NeurIPS 2017 [arxiv] [project page] [code]
Causal and Compositional Generative Models in Online Perception Ilker Yildirim, Michael Janner, Mario Belledonne, Christian Wallraven, Winrich Freiwald, Joshua Tenenbaum CogSci 2017 (oral) [slides]