Appendix

Basic game theory

Cooperative AI by Center for AI Safety

5:05 to 20:32

25 mins

Basic Game Theory

Multi-Agent Reinforcement Learning Foundations And Modern Approaches

'3 Games: Models of Multi-Agent Interaction' up to and excluding '3.3 Stochastic Games

20 mins

Basic Game Theory

Standard Games

Game theory posts from nonzerosum.games

The articles under 'The Classics' except 'The Dilemma's Dilemma'

Prerequisites

Basic Game Theory

30 mins

Standard Games

Intermediate game theory

Extensive form games

‍

The following introduces extensive form games which model scenarios with temporality.

Multiagent Systems: Algorithmic, Game-Theoretic, and Logical Foundations

'5.1 Perfect-information extensive-form games' excluding '5.1.3 Subgame-perfect equilibrium' and '5.1.4 Computing equilibria: backward induction'

Prerequisites

Basic Game Theory

20 mins

Extensive Form Games

Repeated games

‍

Under basic game theory, you will have been introduced to repeated games. The following is a rigorous introduction to repeated games using the extensive form representation of games.

Multiagent Systems: Algorithmic, Game-Theoretic, and Logical Foundations

'6.1 Repeated games' excluding '6.1.3 “Bounded rationality": repeated games played by automata'

Prerequisites

Basic Game Theory

Extensive Form Games

30 mins

Repeated Games

Solution Concepts

‍

This resource explains solution concepts. The chapter '3.4 Further solution concepts for normal-form games' includes descriptions of many important solution concepts and can be used as reference material.

Multiagent Systems: Algorithmic, Game-Theoretic, and Logical Foundations

'3.3 Analyzing games: from optimality to equilibrium' up to and excluding '3.3.3 Finding Nash equilibria'

Prerequisites

Basic Game Theory

15 mins

Solution Concepts

Next is another look at solution concepts beyond the context of normal-form games. The chapter '4 Solution Concepts for Games' also includes descriptions of many important solution concepts and can be used as reference material.

Multi-Agent Reinforcement Learning Foundations And Modern Approaches

'4 Solution Concepts for Games' up to and including '4.2 Best Response'. And '4.4 Nash Equilibrium'

Prerequisites

Basic Game Theory

Markov Games

30 mins

Solution Concepts

Markov Games

‍

Note that Markov games and stochastic games are different terms for the same thing.

Multiagent Systems: Algorithmic, Game-Theoretic, and Logical Foundations

'6.2 Stochastic games' excluding '6.2.3 Computing equilibria'

Prerequisites

Basic Game Theory

10 mins

Markov Games

Multi-Agent Reinforcement Learning Foundations And Modern Approaches

'3.3 Stochastic Games' and '3.4 Partially Observable Stochastic Games'

Prerequisites

Basic Game Theory

20 mins

Markov Games

Fictitious Play and Regret Matching

From 1:02

Prerequisites

Basic Game Theory

15 mins

Fictitious Play

Regret Matching

In the following resource you can skip most of '2.4 Worked Example: Rock-Paper-Scissors'.

An Introduction to Counterfactual Regret Minimization

'2 Regret in Games'

Prerequisites

Basic Game Theory

40 mins

Regret Matching

Machine Learning

But What Is a Neural Network?

All parts

25 mins

Basic Machine Learning

A short introduction to machine learning

All parts

20 mins

Basic Machine Learning

Reinforcement Learning

Reinforcement Learning: Machine Learning Meets Control Theory

All parts

40 mins

Reinforcement Learning

Hugging face Introduction to Deep Reinforcement Learning

Unit 1. Introduction to Deep Reinforcement Learning

1 hr

Reinforcement Learning

Q-Learning

Hugging face Introduction to Q-Learning

Unit 2. Introduction to Q-Learning

Prerequisites

Reinforcement Learning

1 hr 30 mins

Q-Learning

Proximal Policy Optimisation

Hugging face Introduction to Deep Reinforcement Learning

Unit 8. Part 1 Proximal Policy Optimization (PPO)

Prerequisites

Reinforcement Learning

35 mins

Proximal Policy Optimization

Multi-Agent Reinforcement Learning

Multi-Agent Reinforcement Learning Foundations And Modern Approaches

'1 Introduction' up to and excluding '1.4 Challenges of MARL'

Prerequisites

Reinforcement Learning

20 mins

MARL

Large Language Models

Intro to Large Language Models

Up until 21:05

30 mins

LLM

LLM-Based Agents

Foundational Challenges in Assuring Alignment and Safety of Large Language Models

Unit 1. Introduction to Deep Reinforcement Learning

Prerequisites

LLM

20 mins

LLM-Agents