HJ

Leave HJ’s trace, All-In

[Statistics 110] 34. A Look Ahead

Summary, Linearity, Sampling from finite population

[Research Paper] Human-level concept learning through probabilistic program induction

BPL model, whose performance is better than human.

[Hands-On ML] 18. Reinforcement Learning - 4

Variation of Q-Learning, Other RL Algorithms

[Statistics 110] 33. Markov Chains Continued Further

Markov Chains, Google PageRank

[Hands-On ML] 18. Reinforcement Learning - 3

Temporal Difference Learning, Q-Learning, Deep Q-Network