828 views since Nov 26, 2023

TIMESTAMPS
02:00 Why RL/ What is it?
05:26 Aspects of RL
09:38 Our Grid-World Environment
17:00 Cumulative Discounted Rewards
22:00 State Value
34:00 Monte Carlo update
40:00 Temporal Difference Learning
51:40 Exploration Vs Exploitation and the Epsilon Greedy Policy
56:00 Conclusion

In this series we're going to look into the world of Reinforcement Learning!
We'll start at the absolute basics and eventually look at Deep Reinforcement Learning concepts and how we can implement them with Pytorch!

Code and slides here!
https://github.com/LukeDitria/pytorch...