🤖🧠 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.