Reinforcement Learning Crash Course - Introducing Neural Networks into RL | Reinforcement Learning Part-4

The potential that people see in RL is due to the Deep Learning techniques that train Neural Networks to perform very complex behavior. But integrating them into RL comes with a lot of challenges and we are going to get acquainted with some of them. Happy Learning! Cart Pole Gym Environment: https://www.gymlibrary.ml/environments/classic_control/cart_pole/ Project Github link: https://github.com/rajtilakls2510/reinforcement_learning/tree/part_4 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 Music: bensound.com ============================ 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 0:51 - Function Approximation 2:04 - Semi-Gradient Methods 5:14 - Semi-Gradient SARSA 5:59 - CartPole Task 7:36 - Setup 8:12 - Coding Random Agent 12:30 - Coding Semi-Gradient SARSA 24:18 - A Setback 26:38 - Coding an Evaluator 29:36 - Another Setback 32:14 - Reasons for our failure (Outro)