🤖🧠 Analysis of RL-Algorithms on the Sokoban Problem
In this project, I have analyzed Reinforcement Learning solutions to solve a simplified version of the Sokoban environment. The notebook provides a comprehensive guide from installation to result discussion.
- Demonstrating the use of Monte Carlo Off-Policy Control and Deep Q-Network in order to solve the Sokoban environment
- Visualizing the training progress, evaluating the agent's performance, analyzing the learning dynamics and interpreting the results
❗ Note that to properly display images and use intra-document links downloading the repo is necessary.
| Run 1 | Run 2 | Run 3 | Run 4 | Run 5 | Run 6 |
|---|---|---|---|---|---|
 |
 |
 |
 |
 |
 |
| Run 7 | Run 8 | Run 9 | Run 10 | Run 11 | Run 12 |
 |
 |
 |
 |
 |
 |
| Run 13 | Run 14 | Run 15 | Run 16 | Run 17 | Run 18 |
 |
 |
 |
 |
 |
 |
| Run 19 | Run 20 | Run 21 | Run 22 | Run 23 | Run 24 |
 |
 |
 |
 |
 |
 |
| Run 25 | Run 26 | Run 27 | Run 28 | Run 29 | Run 30 |
 |
 |
 |
 |
 |
 |