PinnedTingsong OuinTowards Data ScienceA comparison of Temporal-Difference(0) and Constant-α Monte Carlo methods on the Random Walk TaskThis post discusses the difference between the constant-a MC method and TD(0) methods and compared their performance on the Random Walk…Aug 24, 2023Aug 24, 2023
Tingsong OuinTowards Data ScienceSolving Reinforcement Learning Racetrack Exercise — Building the EnvironmentThe story discusses the solution to the racetrack exercise in the Reinforcement Learning book together.Jul 23, 2023Jul 23, 2023
Tingsong Ou[RL Notes] K-armed Bandits, Part 1This post series includes my notes and code implementations of the knowledge and example of the book Reinforcement Learning 2nd Edition by…May 25, 2023May 25, 2023
Tingsong OuVariational AutoEncoder, and a bit KL Divergence, with PyTorchI. IntroductionDec 31, 20221Dec 31, 20221
Tingsong OuA Simple AutoEncoder and Latent Space Visualization with PyTorchI. IntroductionDec 26, 2022Dec 26, 2022