YoVDO

Combining Tree-Search, Generative Models, and Nash Bargaining Concepts in Game-Theoretic Reinforcement Learning

Offered By: GERAD Research Center via YouTube

Tags

Game Theory Courses Reinforcement Learning Courses Generative Models Courses AlphaZero Courses Monte Carlo Tree Search Courses

Course Description

Overview

Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore a DS4DM Coffee Talk presentation on combining tree-search, generative models, and Nash bargaining concepts in game-theoretic reinforcement learning. Delve into the augmentation of Policy-Space Response Oracles (PSRO) with a novel search procedure using generative sampling of world states and new meta-strategy solvers based on the Nash bargaining solution. Examine the evaluation of PSRO's ability to compute approximate Nash equilibrium and its performance in negotiation games like Colored Trails and Deal or No Deal. Learn about behavioral studies involving human participants negotiating with AI agents, and discover how search with generative modeling enhances policy strength, enables online Bayesian co-player prediction, and produces agents capable of achieving comparable social welfare in human-AI negotiations.

Syllabus

Intro
Motivations
Policy-Space Response Oracles (PSRO) [Lanctot et. al '17] • Maintains a pool of strategies for each player, and iteratively.
Motivated Example: "Deal-or-No-Deal"[1]
Example: Bach or Stravinsky
PSRO on games beyond purely adversarial domains (no search)
Extending AlphaZero to Large Imperfect Information
MCTS in PSRO: A Bayesian Interpretation


Taught by

GERAD Research Center

Related Courses

Visual Recognition & Understanding
University at Buffalo via Coursera
Deep Learning for Computer Vision
IIT Hyderabad via Swayam
Deep Learning in Life Sciences - Spring 2021
Massachusetts Institute of Technology via YouTube
Advanced Deep Learning Methods for Healthcare
University of Illinois at Urbana-Champaign via Coursera
Generative Models
Serrano.Academy via YouTube