StackIt 19 - Introduction to AlphaGoZero
Henning Sperr
StackIt 19 - Introduction to AlphaGoZero
17:58
StackIt 18 - Performance profiling the board and about premature optimization
Henning Sperr
StackIt 18 - Performance profiling the board and about premature optimization
20:00
StackIt 17 - Battle of the giants - MCTS vs AlphaBeta
Henning Sperr
StackIt 17 - Battle of the giants - MCTS vs AlphaBeta
18:55
Halite III - 5 - Success with the first model and finding some more bugs
Henning Sperr
Halite III - 5 - Success with the first model and finding some more bugs
26:49
Halite III - 4 - Debugging the network
Henning Sperr
Halite III - 4 - Debugging the network
33:00
StackIt 15 - Improving MCTS with UCB1
Henning Sperr
StackIt 15 - Improving MCTS with UCB1
33:05
StackIt 16 - Improving the game loop
Henning Sperr
StackIt 16 - Improving the game loop
38:20
StackIt 14 - Implementing Monte Carlo Tree Search
Henning Sperr
StackIt 14 - Implementing Monte Carlo Tree Search
39:19
StackIt 13 - Implementing some sort fo quiescence search
Henning Sperr
StackIt 13 - Implementing some sort fo quiescence search
29:41
StackIt 11 - Losing a full game, with commentary
Henning Sperr
StackIt 11 - Losing a full game, with commentary
17:14
StackIt 12 - Debugging the line of the game
Henning Sperr
StackIt 12 - Debugging the line of the game
11:09
Halite III - 3 - Finalize training and debugging
Henning Sperr
Halite III - 3 - Finalize training and debugging
27:37
Kaggle Titanic - 03 - Deep dive into our variables for logistic regression
Henning Sperr
Kaggle Titanic - 03 - Deep dive into our variables for logistic regression
34:58
Kaggle Titanic - 02 - Cleanup and add our first categorical
Henning Sperr
Kaggle Titanic - 02 - Cleanup and add our first categorical
30:08
Halite III - 1 - Setup of training
Henning Sperr
Halite III - 1 - Setup of training
43:50
Halite III - 2 - Building the Game/Training loop
Henning Sperr
Halite III - 2 - Building the Game/Training loop
30:05
Halite III - 0 - Deep Reinforcement Learning - Introduction
Henning Sperr
Halite III - 0 - Deep Reinforcement Learning - Introduction
16:16
StackIt 10 - Making the code a bit messy on my way to clean it up
Henning Sperr
StackIt 10 - Making the code a bit messy on my way to clean it up
34:30
StackIt 9 - Transposition Table v2 short
Henning Sperr
StackIt 9 - Transposition Table v2 short
9:43
StackIt 8 - Ramble Ramble & Hashtables
Henning Sperr
StackIt 8 - Ramble Ramble & Hashtables
31:25
Kaggle Titanic - 01 - Intro to the data and a first submission
Henning Sperr
Kaggle Titanic - 01 - Intro to the data and a first submission
33:20
StackIt 7 - Board string representation and a couple of games
Henning Sperr
StackIt 7 - Board string representation and a couple of games
37:38
StackIt 6 - Cleanup, Import mess and pretty printing
Henning Sperr
StackIt 6 - Cleanup, Import mess and pretty printing
34:26
StackIt 5 - AlphaBeta and my first win & loss and strangeness
Henning Sperr
StackIt 5 - AlphaBeta and my first win & loss and strangeness
29:33
StackIt 4 - Implementing perft, principle variation and some stats
Henning Sperr
StackIt 4 - Implementing perft, principle variation and some stats
34:51
StackIt 3 - Implementation of MinMax
Henning Sperr
StackIt 3 - Implementation of MinMax
40:13
StackIt 2 - Finished the board and prep for MinMax
Henning Sperr
StackIt 2 - Finished the board and prep for MinMax
32:16
StackIt 1 - Intro and first part of the Board
Henning Sperr
StackIt 1 - Intro and first part of the Board
33:57
Kaggle - CrowdFlower - 01 - Introduction and basic bag of words.
Henning Sperr
Kaggle - CrowdFlower - 01 - Introduction and basic bag of words.
43:38
KaggleCrowdFlower - 02 - First Classification
Henning Sperr
KaggleCrowdFlower - 02 - First Classification
35:13