Published Oct 2, 2023

Agents with Theory of Mind Play Hanabi

Explore the intersection of AI and game theory as Ph.D. student Nieves Montes delves into how the cooperative card game Hanabi enhances AI models through theory of mind and abductive reasoning, highlighting the potential for multi-agent systems in competitive scenarios.

Episode Highlights

Topics covered

Episode Highlights

Related Episodes

AI Fails on Theory of Mind Tasks
Answers 383 questions
AI in Games
Answers 383 questions
Game Theory
Answers 383 questions
Brain Inspired AI
Answers 383 questions
The Agent Model of Artificial Intelligence
Answers 383 questions
The Imitation Game
Answers 383 questions
[MINI] Reinforcement Learning
Answers 383 questions
Decentralized Information Gathering
Answers 383 questions
AI Decision-Making
Answers 383 questions
[MINI] Multi-armed Bandit Problems
Answers 383 questions
Evaluating AI Abilities
Answers 383 questions
Consensus Voting
Answers 383 questions
Octopus Cognition
Answers 383 questions
[MINI] Entropy
Answers 383 questions
Interpretable One Shot Learning
Answers 383 questions

Dexa/Kyle Polich

Agents with Theory of Mind Play Hanabi

Topics covered

Popular Clips

Graduating and Beyond

Using Theory of Mind

Theory of Mind and Abduction

Analyzing Agent Performance

Changing Minds, Abductive Logic

Pushing the Limits

Evolving Multi Agent Systems

Theory of Mind Benefits

Reasoning about Beliefs

Hanabi: Cooperative Card Game

Episode Highlights

Understanding Hanabi

Theory of Mind

Abductive Reasoning

Related Episodes

AI Fails on Theory of Mind Tasks

AI in Games

Game Theory

Brain Inspired AI

The Agent Model of Artificial Intelligence

The Imitation Game

[MINI] Reinforcement Learning

Decentralized Information Gathering

AI Decision-Making

[MINI] Multi-armed Bandit Problems

Evaluating AI Abilities

Consensus Voting

Octopus Cognition

[MINI] Entropy

Interpretable One Shot Learning

Agents with Theory of Mind Play Hanabi

Topics covered

Popular Clips

Episode Highlights

Understanding HanabiNieves Montes, a Ph.D. student at the Artificial Intelligence Research Institute, discusses the cooperative card game Hanabi and its implications for AI research. She explores how the game's mechanics can enhance AI models by incorporating theory of mind and abductive reasoning.

Understanding Hanabi

Theory of MindNieves Montes discusses the application of theory of mind in AI, focusing on its use in multi-agent systems like Hanabi. She examines the benefits and challenges of deeper nesting in theory of mind, highlighting its potential in competitive domains.

Theory of Mind

Abductive ReasoningNieves Montes explores the integration of abductive reasoning with theory of mind in AI, enhancing agents' ability to infer and adapt. This approach improves agent performance in tasks like the game Hanabi, offering advantages in communication efficiency and interpretability.

Abductive Reasoning

Related Episodes