AI Race Cars
Mentors :
Kritin Agarwal
Yash Shah
Mentees :
6(freshies) + 4(sophies and above)
In this project, we’ll build an AI Race Car bot from scratch, and implement both basic Reinforcement Learning and Deep Reinforcement Learning techniques to achieve high scores.
Reinforcement learning (RL) is an area of machine learning concerned with how intelligent agents ought to take actions in an environment in order to maximize the notion of cumulative reward. A reinforcement learning agent is capable of learning on its own by exploring its environment to determine the best action to take in a certain situation.
For some cool stuff - https://www.youtube.com/watch?v=Zeyv1bN9v4A&ab_channel=UZHRoboticsandPerceptionGroup
Prerequisites:
For freshies: Basic knowledge of python and lots of enthusiasm
For sophies: Intermediate knowledge of python and ML
Tentative Timeline :
| Week | Work |
|---|---|
| Week 1 | Introduction to basic Reinforcement learning, MDP, and Dynamic Programming |
| Week 2-3 | Getting familiarized with Open AI gym environments |
| Week 4-5 | Learning various RL algorithms like DQN, PPO, A3C |
| Week 6-7 | Deploying algorithms on simpler problems and car racing |
| Week 8-9 | Further advancements by tuning hyperparameters, improving scores |
