🚀 Welcome to the Multi-Agent Reinforcement Learning & Agentic AI Course! 🤖🧠

This repository will be your central hub for all course materials, including:

• 📜 Lecture Slides & Notes: Access all presentation materials and supplementary notes here.
• 💻 Code & Tutorials: Find Jupyter notebooks, Python scripts, and practical examples to help you grasp key concepts and implement algorithms.
• 📚 Reading Materials: Links to relevant research papers, book chapters, and other useful resources.

This course focuses on multi-agent systems, how reinforcement learning drives intelligent decision-making in complex settings, and the emerging area of agentic AI. We will cover core theories, recent research advancements, and their practical applications.

---

Topics covered:

Topic 1: MARL

• RL (MDP, Value iteration, Policy iteration, Q-learning)
• Deep RL (Deep Q-learning, DDQN, Policy Gradient Methods: Actor-Critic, PPO)
• Games as models of multi-agent interaction (Normal form games, Stochastic Games, POSG)
• Solution Concepts (Equilibrium, equilibrium refinement)
• MARL Challenges
• MARL in Games
• Deep MARL

Topic 2: Agentic AI

• Intro to LLM agents, group chat, MCP
• Planning and Control
• Agentic software development

---

Resources:

RL:

• Reinforcement Learning: An Introduction by Barto and Sutton, available here: http://incompleteideas.net/book/the-book-2nd.html
• Gymnasium: https://gymnasium.farama.org/
• TF-agents: https://www.tensorflow.org/agents/
• TorchRL: https://docs.pytorch.org/rl/stable/index.html
• StableBaselines3 (based on PyTorch, also in Jax): https://stable-baselines3.readthedocs.io/en/master/index.html

MARL:

• Multi-Agent Reinforcement Learning: Foundations and Modern Approaches by Stefano V. Albrecht, Filippos Christianos and Lukas Schafer, available here: http://marl-book.com
• PettingZoo: https://pettingzoo.farama.org/
• MARLLib: https://marllib.readthedocs.io/en/latest/
• Mava: https://github.com/instadeepai/Mava