Not logged in
CSS-Forum
Forum
CSS-Online
Help
Search
Login
CSS-Shop
Impressum
Datenschutz
Topic
Hauptforen
/
CSS-Forum
/ Lesestoff zum Reinforcement Learning
By
Lothar Jung
Date
2020-01-03 08:52
Upvotes
3
Aus einem Beitrag auf Discord:
A general reinforcement learning algorithm that masters chess, shogi and Go through self-play:
<
https://deepmind.com/documents/260/alphazero_preprint.pdf
>
Mastering the game of Go with Deep Neural Networks & Tree Search:
<
https://deepmind.com/research/publications/mastering-game-go-deep-neural-networks-tree-search/
>
Mastering the game of Go without Human Knowledge:
<
https://deepmind.com/research/publications/mastering-game-go-without-human-knowledge/
>
Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm:
<
https://arxiv.org/abs/1712.01815
>
Efficient selectivity and backup operators in Monte-Carlo tree search:
<
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.81.6817
>
Bandit based Monte-Carlo Planning:
<
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.102.1296
>
Train longer, generalize better: closing the generalization gap in large batch training of neural networks:
<
https://arxiv.org/abs/1705.08741
>
Squeeze-and-Excitation Networks:
<
https://arxiv.org/abs/1709.01507
>
Topic
Hauptforen
/
CSS-Forum
/ Lesestoff zum Reinforcement Learning
Forum
Hauptforen
- CSS-Forum
- Schachprogrammierung
- Schachcomputer
- CSS-OM-Forum
- Blogs
Hilfe und Unterstützung
- Support-Forum
Powered by
mwForum
2.29.3 © 1999-2014 Markus Wichitill