This is a specially organized "Minecraft team jam" at the (usually not recorded) weekly journal club "Deep Learning: Classics and Trends" (mlcollective.org/dlct/ ).
Speaker: VPT team, MineDojo team, EvoCraft team
Title: Minecraft team jam
Abstract: Lately, we’ve all noticed a good amount of exciting research around Minecraft, coming from various teams with different focuses: VPT [1], MineDojo [2], and Evocraft [3]. We feel the need as a community to discuss this research direction in a shared and open space.
It is, however, rather rare that different research teams get together to jam about similar work they are doing - such opportunities only exist in formal conference workshops, which involves a rather long and painful cycle to plan and execute.
Luckily, DLCT is a weekly running, reputable platform with a strong base of audience who are active, curious, and eager to learn. We host paper presentations and occasional panel discussions with an aim to grow together in ML knowledge and expertise.
Therefore, we are interested in hosting a cross-team jam session to discuss
- why should we care about Minecraft
- what can we learn from large-scale pre-training
- why is Minecraft a great framework for the open-ended learning
[1] VPT: tweet, blog, paper
[2] MineDojo: tweet, website, paper
[3] Evocraft competition: website, paper
Speakers:
Linxi "Jim" Fan is an NVIDIA AI research scientist at Senior Director Anima Anandkumar’s group. His primary focus is to develop generally capable autonomous agents. To tackle this grand challenge, his research efforts span foundation models, policy learning, robotics, multimodal learning, and large-scale systems. He obtained his Ph.D. degree in Computer Science from Stanford University, advised by Prof. Fei-Fei Li. His Ph.D. thesis was titled "Training and Deploying Visual Agents at Scale". Previously, Jim did research internships at NVIDIA, Google Cloud AI, OpenAI, Baidu Silicon Valley AI Lab, and Mila-Quebec AI Institute. He graduated summa cum laude with a Bachelor's degree in Computer Science from Columbia University. Jim was the Valedictorian of Class 2016 and a recipient of the Illig Medal at Columbia.
Yuke Zhu is an Assistant Professor in the Computer Science department of UT-Austin and a senior research scientist at NVIDIA. His research lies at the intersection of robotics, machine learning, and computer vision. He received his Master’s and Ph.D. degrees from Stanford University. His research works have won several awards and nominations, including the Best Conference Paper Award in ICRA 2019, Outstanding Learning Paper at ICRA 2022, and Best Paper Finalists in IROS 2019, 2021. He is the recipient of the NSF CAREER Award and the Amazon Reward Awards.
Sebastian Risi is a Professor at the IT University of Copenhagen where he directs the Creative AI Lab, and co-directs the Robotics, Evolution and Art Lab (REAL). Sebastian received his PhD from the University of Central Florida in 2012. He has won several international scientific awards, including multiple best paper awards, the Distinguished Young Investigator in Artificial Life 2018 award, a Google Faculty Research Award in 2019, and an Amazon Research Award in 2020. His interdisciplinary work has been published in major machine learning, artificial life, and human-computer interaction conferences and has been covered by various media outlets, including Science, New Scientist, Wired, Fast Company, and The Register. In addition to his academic career, Sebastian is a co-founder of modl.ai, a company that lets game developers rapidly create and test their games through AI-driven approaches.
Jeff Clune is an Associate Professor of computer science at the University of British Columbia and a Faculty Member of the Vector Institute. Before those roles, he was a research manager at OpenAI and a Senior Research Manager and founding member of Uber AI Labs, which was formed after Uber acquired a startup Jeff was a part of. Jeff focuses on deep learning, including deep reinforcement learning. Prior to Uber, he was the Loy and Edith Harris Associate Professor in Computer Science at the University of Wyoming. Before that he was a Research Scientist at Cornell University and received degrees from Michigan State University (PhD, master’s) and the University of Michigan (bachelor’s). More on Jeff’s research can be found at JeffClune.com or on Twitter (@jeffclune).