CSL Seminar - Yi Wu - Language Model Meets Reinforcement Learning: Building Strong Language Agents for Strategic Gameplay

Speaker: Yi Wu , Tsinghua University

Date: Wednesday, December 06, 2023

Time: 2:00 PM to 3:00 PM Note: all times are in the Eastern Time Zone

Public: Yes

Location: Seminar Room G575

Event Type: Seminar

Room Description:

Host: Tongzhou Wang, CSAIL MIT

Contact: Tongzhou Wang, tongzhou@csail.mit.edu

Relevant URL:

Speaker URL: https://jxwuyi.weebly.com/

Speaker Photo:

Reminders to: tongzhou@mit.edu, jxwuyi@mail.tsinghua.edu.cn, ei-seminars@lists.csail.mit.edu, lids-seminars@mit.edu, robotics@mit.edu, jxwuyi@gmail.com, seminars@csail.mit.edu

Reminder Subject: TALK: Yi Wu - Language Model Meets Reinforcement Learning: Building Strong Language Agents for Strategic Gameplay #event

Computational Sensorimotor Learning (CSL) Seminar

1-on-1 meeting sign-up: https://docs.google.com/spreadsheets/d/1riA5Bg72BAaZNokW9JAdHyM8fnwxbK0fhjgRHOm8lyI/edit?usp=sharing

Zoom: https://mit.zoom.us/j/96702680180?pwd=cXNJTmh2QmdLc2JENDFOWWU5OTc0dz09

Abstract:
Thanks to the advances in large language models (LLM), there has been a recent trend to develop intelligent language agents for complex tasks. Most existing applications of language agents are purely LLM-based, i.e., by directly prompting LLMs to output actions. Although interesting emergent behaviors can be observed, their performances in complex multi-agent games can be limited due to the lack of domain-specific training.
This talk will cover some recent projects in my group on developing language agents that can both yield strong gameplay performances and cooperate with real human players in challenging multi-agent games. The key idea is to combine language modeling and reinforcement learning. The language model will serve as an interface for reasoning and interpreting high-level commands while reinforcement learning helps substantially improve the gameplay performance of the agent.
We demonstrate our agents in three domains, including an agent that can follow high-level commands to play a real-time strategy game, an Overcooked agent that can cooperate with humans via languages to cook dishes, and an agent that outperforms average human players in the Werewolf game.

Bio:
Yi Wu is now an assistant professor at the Institute for Interdisciplinary Information Sciences (IIIS) at Tsinghua University. He obtained his Ph.D. degree from UC Berkeley in 2019 under the supervision of Prof. Stuart Russell. Before moving back to Tsinghua, Yi was a full-time researcher at OpenAI. His research focuses on improving the generalization capabilities of learning agents. He is broadly interested in a variety of topics in AI, including multi-agent reinforcement learning, human-AI interaction, language grounding, and robot learning. His representative works include the MADDPG/MAPPO algorithm, OpenAI's hide-and-seek project, and the value iteration network, which won the best paper award at NIPS 2016.

Yi's Website: https://jxwuyi.weebly.com/

Research Areas:
AI & Machine Learning

Impact Areas:

This event is not part of a series.

Created by Tongzhou Wang at Sunday, November 26, 2023 at 8:13 PM.