Welcome to the official repository for the AI Masters 2025 Reinforcement Learning Course! This repo contains all lecture slides, seminar materials, and homework assignments for the course. Whether you're a student, a fellow instructor, or an RL enthusiast, you'll find everything you need to dive deep into the world of Reinforcement Learning.
This course covers the fundamentals and advanced topics of Reinforcement Learning (RL), including Markov Decision Processes, Dynamic Programming, Temporal Difference Learning, Deep RL, Policy Gradients, Multi-Agent Systems, Offline RL, and practical applications. The course is designed for graduate students and professionals eager to master RL both in theory and practice.
| # | Date | Topic | PDF Link |
|---|---|---|---|
| 1 | 09/02/2026 | Introduction, Markov Decision Process | |
| 2 | 16/02/2026 | Dynamic Programming | |
| 3 | 02/03/2026 | Temporal Differences | |
| 4 | 16/03/2026 | Approximation, Deep Q-Network, Rainbow Extensions | |
| 5 | 23/03/2026 | Policy Gradient Optimization, Actor-Critic (PG, REINFORCE, A2C) | |
| 6 | 30/03/2026 | Advanced Actor-Critic Methods (TRPO, PPO, GAE) | |
| 7 | 06/04/2026 | Continuous Action Space (DDPG, TD3, SAC) | |
| 8 | 13/04/2026 | Multi-Agent Reinforcement Learning (IDQN, IPPO, QMIX, MAPPO) | |
| 9 | 27/04/2026 | Integrating Reinforcement Learning and Planning | |
| 10 | 20/04/2026 | Learning from Demonstrations. Transformers in RL | PDF-2025 |
| 11 | 04/05/2026 | Linear Dynamical Systems | PDF-2025 |
| 12 | 18/05/2026 | Practical Applications of RL, GRPO | PDF-2025 |
| # | Topic | Folder Link |
|---|---|---|
| 1 | Cross Entropy | seminar_01_cross_entropy |
| 2 | Value Iteration | seminar_02_value_iteration |
| 3 | Q-Learning, SARSA, TD(λ) | seminar_03_q_learning_sarsa_td_lambda |
| 4 | Deep Q-Networks | seminar_04_dqn |
| 5 | REINFORCE, Actor-Critic | seminar_05_reiforce_actor_critic |
| 6 | PPO | seminar_06_ppo |
| 7 | DDPG, TD3, SAC | seminar_07_ddpg_td3_sac |
| 8 | QMIX | TBA |
| 9 | Decision Transformer | TBA |
| 10 | MCTS | TBA |
| 11 | LQR | TBA |
| 12 | GRPO, SFT | TBA |
| # | Topic | Folder Link |
|---|---|---|
| 1 | homework_1 | homework_1 |
| 2 | homework_2 | homework_2 |
| 3 | homework_3 | homework_3 |
| 4 | homework_4 | homework_4 |
| 5 | homework_5_ppo | homework_5_ppo |
| 6 | homework_5_sac | homework_5_sac |
| 7 | homework_6_dt_mem | homework_6_dt_mem |
- Browse the Lectures section for slides and theory.
- Explore the Seminars for hands-on coding and problem-solving sessions.
- Complete the Homeworks to reinforce your understanding and gain practical RL experience.
Feel free to fork, clone, or star this repository. Contributions and feedback are always welcome!
Happy Reinforcement Learning!