Nieves Montes, Ph.D. student specializing in value-based reasoning and theory of mind, discusses her latest research on combining theory of mind and abductive reasoning in agent-oriented programming. The podcast explores the mechanics and challenges of Hanabi, the relationship between theory of mind and abduction, using predicate logic to represent desire and motivation in an agent, reasoning about other players in Hanabi, and future plans and online presence.
Read more
AI Summary
AI Chapters
Episode notes
auto_awesome
Podcast summary created with Snipd AI
Quick takeaways
Hanabi's gameplay requires implicit theory of mind and multi-agent systems approach to understand others' perspectives and make advantageous moves.
Multi-agent systems cut across various sub-fields of AI, accommodating the interaction and behavior of different agents.
Deep dives
Overview of Hanabi and its Unique Gameplay
Hanabi is a cooperative game where players work together to build stacks of cards based on color and rank. Each player has private information in their hand and common information on the board. The challenge lies in the limited communication players can have and the rules governing the information exchange. Hanabi's gameplay requires implicit theory of mind and multi-agent systems approach to understand others' perspectives and make advantageous moves.
The Broad Evolution of Multi-Agent Systems
Multi-agent systems have evolved over the years, adapting to different techniques and methodologies. Initially, symbolic and logic-based agents were popular, but now multi-agent reinforcement learning with neural networks and machine learning models is prevalent. Multi-agent systems cut across various sub-fields of AI, accommodating the interaction and behavior of different agents.
Research Focus in the AI Department
The AI department at the Artificial Intelligence Research Institute in Barcelona focuses on areas such as electronic institutions, agreement technologies, coordination, distribution, and recently, values and ethical considerations in AI. The department has broadened its research to address the societal impact and ethical implications of AI technologies.
The TOMABD Agent Model and Value-Based Reasoning
The TOMABD (Theory of Mind Abduction) agent model integrates theory of mind and abduction into multi-agent systems. It enables agents to reason about the mental states of other players and infer explanations for observations. Using a logical language, the agents represent beliefs and update them based on perceptions. The TOMABD model emphasizes easy interpretability and allows for tuning the level of theory of mind reasoning based on domain requirements.
Nieves Montes, a Ph.D. student at the Artificial Intelligence Research Institute in Barcelona, Spain, joins us. Her PhD research revolves around value-based reasoning in relation to norms. She shares her latest study, Combining theory of mind and abductive reasoning in agent‑oriented programming.
Get the Snipd podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered podcast player
Listen to all your favourite podcasts with AI-powered features
Discover highlights
Listen to the best highlights from the podcasts you love and dive into the full episode
Save any moment
Hear something you like? Tap your headphones to save it with AI-generated key takeaways
Share & Export
Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more
AI-powered podcast player
Listen to all your favourite podcasts with AI-powered features
Discover highlights
Listen to the best highlights from the podcasts you love and dive into the full episode