Reinforcement learning, tabular to deep
From MDPs and Sarsa to SAC, TD3 and Rainbow, implemented during the MSc.
[00][What this figure measures]
[00][What this figure measures]
[00][What this figure measures]
[Main image: screenshot, diagram or photo. 1600 × 900 px]
Context
[Where and why the project started: employer, course or competition, and the people involved.]
[The constraints: deadline, data available, tools imposed, confidentiality.]
Problem
[The precise problem, and why the existing solutions were not enough.]
Approach
[What you built, in three or four sentences. Name the main components.]
- [Design decision 1, and why you chose it over the alternative]
- [Design decision 2, and why]
- [Design decision 3, and why]
[Architecture diagram or pipeline schematic]
Results
[The main result, with a number and the baseline it is compared to.]
[How it was evaluated: data, baseline, protocol, and who validated it.]
[Results table or chart]
Limits and next steps
- [What does not work yet, or the known limits of the result]
- [What you would do differently]
- [The next step, if the project continues]
Stack
- Polytechnique Montréal
- 2024
- [Add a tool]
Links
[Code repository][Demo or video][Paper, report or slides]
Gallery
[Image 1, with a one-line caption]
[Image 2, with a one-line caption]
[Image 3, with a one-line caption]