Intro to Reinforcement Learning
NumPy
Optuna
GymnasiumMy interest in Reinforcement Learning (RL) has been steadfast ever since watching the Hide & Go seek video by OpenAI. When DeepMind released AlphaGo and AlphaStar, I was exposed to, and excited by, the application of this new technology to games. After building my bbrbattle site, I speculated that the application of RL could optimize its functionality, and would potentially allow myself and other players to discover new optimal strategies.
In this course I learned a variety of algorithms to apply to different toy RL environments. I learned how to construct my own custom environment, as well as many different on and off-policy algorithms to apply to them. I learned the difference between training a policy compared to a state-value function, how imitation learning works, as well as different training policies such as temporal learning and monte-carlo methods.
Certificate coming soon...