Research types of models used for game actors

[Klazkin]

Research the specifics of model architectures used for making decisions in games such as chess and go. Find out what layers make up models such as AlphaGo and AlphaZero, as well as what other solutions/alternatives exist.

Time tracking

Time Estimate: 2 hours 0 minutes Time spent: 2 hours 30 minutes

Resources

1. DeepChess: End-to-End Deep Neural Network for Automatic Learning in Chess https://www.cs.tau.ac.il/~wolf/papers/deepchess.pdf
2. Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm https://arxiv.org/pdf/1712.01815.pdf
3. OpenAI Five Architecture
4. AlphaZero (Connect4)
5. AlphaZero: Shedding new light on chess, shogi, and Go https://deepmind.google/discover/blog/alphazero-shedding-new-light-on-chess-shogi-and-go/
6. Multiple Policy Value Monte Carlo Tree Search https://arxiv.org/pdf/1905.13521v1.pdf
7. Restricted Boltzmann Machine (RBM) with Practical Implementation https://medium.com/machine-learning-researcher/boltzmann-machine-c2ce76d94da5
8. Predicting Professional Players’ Chess Moves with Deep Learning https://towardsdatascience.com/predicting-professional-players-chess-moves-with-deep-learning-9de6e305109e
9. Checkmating One, by Using Many: Combining Mixture of Experts with MCTS to Improve in Chess https://arxiv.org/pdf/2401.16852.pdf