Monte Carlo Tree Search

[LLM Paper Club] Llama 3.1 Paper: The Llama Family of Models

Latent Space

A technique used in conjunction with stepwise reward models to improve reasoning traces in large language models.

AI Won't Be AGI, Until It Can At Least Do This (plus 6 key ways LLMs are being upgraded)

AI Explained

David Silver: AlphaGo, AlphaZero, and Deep Reinforcement Learning | Lex Fridman Podcast #86

Lex Fridman

A heuristic search algorithm for some decision processes, used in games and AI, that evaluates positions by simulating random playouts.

Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI | Lex Fridman Podcast #75

Lex Fridman

A heuristic search algorithm for decision processes, often used in game AI, which provides an approximation for the planning part of AIXI.

Demis Hassabis: Future of AI, Simulating Reality, Physics and Video Games | Lex Fridman Podcast #475

Lex Fridman

A search algorithm used in AI, notably in AlphaGo to find novel strategies like 'move 37', and envisioned for use in hybrid systems with LLMs.

MIT 6.S094: Deep Reinforcement Learning

Lex Fridman

A heuristic search algorithm used for decision-making in game playing and other domains, particularly effective in large state spaces.

Noam Brown: AI vs Humans in Poker and Games of Strategic Negotiation | Lex Fridman Podcast #344

Lex Fridman

A type of search algorithm crucial for game AIs like AlphaGo, involving simulating games to evaluate moves, but noted as less effective for imperfect information games like poker.