rl-analysis

This repo is the feeder repo for my Senior Semester Project (BTech Project) at IIT Dharwad. It contains all the code, weights and helper files mentioned in the report.

Each folder contains the following

1. The code for each agent mentioned in the report
2. The environment and requirements to run the code
3. The checkpoints/weights for agents (if applicable)

YouTube Gameplays

Cross Entropy Method on Simple Tetris (20x10) - https://youtu.be/_TyaqHpXj8A

Monte-Carlo Tree Search on Snake - https://www.youtube.com/watch?v=cSrcp2q0Guk

Table-based Q-learning on Snake - https://www.youtube.com/watch?v=LRqSywQ7zlg

Advantage Actor-Critic Agent on Pong (using 200 neurons) - https://www.youtube.com/watch?v=sag9fY-Kw2Q

Advantage Actor-Critic Agent on Simple Tetris (20x10) - https://www.youtube.com/watch?v=Mv-FARYb_pE

Advantage Actor-Critic Agent on Simple Tetris (20x6) - https://www.youtube.com/watch?v=QpQa2GiNZyM