Imitation Learning: Single & Multi-Agent

• Introduction
• Schedule
• Organizer
• Sponsor

Introduction

In the paradigm of Reinforcement Learning (RL), an agent learns from the reward feedback when interacting with the environment. However, it remains a challenge to design proper reward functions for complex tasks in real life. To that end, Imitation Learning (IL), also known as Learning from Demonstration (LfD), acts as an alternative method to learn policies without any reward signal and make better use of existed exert demonstrations. Besides, it is observed both theoretically and empirically that IL can help agent learn a sub-optimal policy in a more data-efficient way than RL. Not only for single-agent tasks, IL also helps agents learn in multi-agent settings, where the expert demonstrations are interactions among agents. Our workshop is a half-day workshop on Imitation Learning at DAI 2020, with the aim to provide a venue, which can bring together academia researchers and industry practitioners (i) to discuss the principles, limitations and applications of IL for both single-agent and multi-agent scenarios, and (ii) to foster research on innovative algorithms, novel techniques, and new applications of IL.

Schedule

Overall Program

Keynote

Towards Real-World Imitation Learning: Animation, Sports Analytics, Robotics, and More
Yisong Yue, California Institute of Technology
Time: 9:10-9:50 (GMT+8), 18:10-18:50 (PST)
Bio: Yisong Yue is a professor of Computing and Mathematical Sciences at the California Institute of Technology. He was previously a research scientist at Disney Research. Before that, he was a postdoctoral researcher in the Machine Learning Department and the iLab at Carnegie Mellon University. He received a Ph.D. from Cornell University and a B.S. from the University of Illinois at Urbana-Champaign.

Regular Talks

From Imitation Learning to Offline RL to Deployment-Efficient RL
Shane Shixiang Gu, Google Brain
Time: 9:50-10:20 (GMT+8), 18:50-19:20 (PST)
Bio: Shane Shixiang Gu is a Research Scientist at Google Brain, where he does research in deep learning, reinforcement learning, robotics, and probabilistic machine learning. He holds PhD in Machine Learning from the University of Cambridge in the UK and the Max Planck Institute for Intelligent Systems in Tübingen Germany, during which he was co-supervised by Richard E. Turner, Zoubin Ghahramani, and Bernhard Schölkopf and collaborated with Sergey Levine/Ilya Sutskever at UC Berkeley/Google Brain and Timothy Lillicrap at DeepMind as a student researcher.

A Density Estimation Approach to Imitation Learning
Kuno Kim, Stanford University
Time: 10:20-10:50 (GMT+8), 19:20-19:50 (PST)
Bio: Kuno Kim is a Ph.D candidate in the Department of Computer Science at Stanford University advised by Stefano Ermon and is a member of the Stanford Artificial Intelligence Lab (SAIL) and Statistical Machine Learning Group. His research spans topics of Imitation Learning, Inverse Reinforcement Learning, Probabilistic Inference in Control, and Deep Generative Models. Recently, he has focused on developing more stable and scalable Imitation Learning algorithms with applications in robotics. Prior to Stanford, he received a B.S degree from the California Institute of Technology in 2016.

Advances in Multi-Agent Imitation Learning
Minghuan Liu, Shanghai Jiao Tong University
Time: 10:50-11:20 (GMT+8), 19:50-20:20 (PST)
Bio: Minghuan Liu is a second-year Ph.D. student in Shanghai Jiao Tong University supervised by professor Weinan Zhang. His research mainly focuses on the general area of reinforcement learning, particularly in imitation learning and multi-agent systems.

A Deeper Look at BC and Adversarial based Methods
Tian Xu, Nanjing University
Time: 11:20-11:50 (GMT+8), 20:20-20:50 (PST)
Bio: Tian Xu is a second-year Ph.D. student in the school of artificial intelligence in Nanjing University. He is fortunate to be advised by professor Yang Yu. His research mainly focuses on the theoretical guarantees of reinforcement learning (RL). In particular, he is interested in statistical and optimization aspects of RL.

Organizer

Sponsor

Copyright © 2020.Shanghai Jiao Tong University. This page was generated by GitHub Pages using the Architect theme by Jason Long.