Lesson Plan
The lesson plan for this course is divided into five (5) blocks. For each block the following activities are planned.
Attention!
The schedule is always subject to changes and adaptations as the course is executed.
Introduction to Reinforcement Learning and Review of Autonomous Agents
| Date | Content | Activities |
|---|---|---|
| Feb 10 | Course presentation and Introduction to Reinforcement Learning | Lecture with discussion and exercise solving |
| Feb 12 | Sequencial Decision Making with Evaluative Feedback | Lecture with discussion and exercise solving |
| Feb 19 | Markov Decision Process | Lecture with discussion and exercise solving |
Tabular Algorithms (Q-Learning and Sarsa)
| Date | Content | Activities |
|---|---|---|
| Feb 24 | Q-Learning algorithm. Tools and environments for RL | Lecture with implementation guidelines |
| Feb 26 | Q-Learning algorithm, tools for Reinforcement Learning and environments | Lecture with implementation guidelines |
| Mar 3 | SARSA algorithm | Lecture with implementation guidelines |
| Mar 5 | How to evaluate agent performance and learning curves | Lecture with implementation guidelines |
| Mar 10 | Using RL in non-deterministic environments | Problem presentation and group implementation |
| Mar 12 | Review: Q-Learning, SARSA, deterministic and non-deterministic environments, agent evaluation | Classroom discussion about obtained results |
Deep Reinforcement Learning: value-based and policy gradient
| Date | Content | Activities |
|---|---|---|
| Mar 17 | Implementing an agent for complex environments | Lecture with implementation guidelines |
| Mar 19 | Deep Q-Learning | Lecture with implementation guidelines |
| Mar 24 | Variants of the Deep Q-Learning algorithm | Lecture with implementation guidelines |
| Apr 7 | Variants of the Deep Q-Learning algorithm | Lecture with implementation guidelines |
| Apr 9 | REINFORCE algorithm | Lecture with implementation guidelines |
| Apr 14 | Review and discussion of results obtained from recent APSs | Lecture with implementation guidelines |
| Apr 16 | Project description | The students will delivery a draft paper |
Deep Reinforcement Learning: actor-critic
| Date | Content | Activities |
|---|---|---|
| Apr 23 | Actor-Critic (A2C) | Lecture with implementation guidelines |
| Apr 28 | Proximal Policy Optimization (PPO) | Lecture with implementation guidelines |
| Apr 30 | Review and discussion of results obtained from recent APSs | Lecture with implementation guidelines |
Final Project
| Date | Content | Activities |
|---|---|---|
| May 05 | Project development | Studio class for project execution |
| May 07 | Project development | Studio class for project execution |
| May 12 | Project development | Studio class for project execution |
| May 14 | Project development | Studio class for project execution |
| May 19 | Project Presentations Seminar | Project Presentations Seminar |
| May 21 | Project Presentations Seminar | Project Presentations Seminar |
| May 26 | Assessment | Final assessment |