Reinforcement Learning Crash Course - Design the Best Reward Function | Reinforcement Learning Part-6

In this video, we finally get to the point of training the long waited Lunar Lander Problem. But to do that, we have to write very good reward functions to make our training process faster and easier for the agent to learn. We study Shaped Rewards and their advantages over Sparse Rewards and find out some pretty interesting stuff. Happy Learning! Lunar Lander Environment: https://www.gymlibrary.ml/environments/box2d/lunar_lander/ Github Project Link: https://github.com/rajtilakls2510/reinforcement_learning/tree/part_6 Reinforcement Learning Book by Sutton and Barto: http://incompleteideas.net/book/the-book.html Free Reinforcement Learning Course from IIT Madras: https://nptel.ac.in/courses/106106143 👍If you find this video helpful, consider giving it a thumbs up and subscribing for more educational videos on data science! 💭Share your thoughts, experiences, or questions in the comments below. I love hearing from you! ============================ Do you want to learn from me? Check my affordable mentorship program at : https://learnwith.campusx.in ============================ 📱 Grow with us: CampusX' LinkedIn: https://www.linkedin.com/company/campusx-official CampusX on Instagram for daily tips: https://www.instagram.com/campusx.official My LinkedIn: https://www.linkedin.com/in/nitish-singh-03412789 Discord: https://discord.gg/PsWu8R87Z8 ⌚Time Stamps⌚ 0:00 - Intro 0:50 - The Reward Function 5:03 - Classification of Reward Functions 6:12 - Shaped Rewards for CartPole 10:07 - Shaped Rewards for Mountain Car 14:11 - Better Rewards for Mountain Car 17:02 - Lunar Lander Problem 19:47 - Coding Lunar Lander Trainer 24:05 - Training Results 26:24 - What Next! 27:42 - Outro