notes-cog-ai
* [Self:notes-cog-ai-workingMemoryAsCacheCoherency workingMemoryAsCacheCoherency] * [Self:notes-cog-ai-aiNotes . . .
3K - last updated 2021-02-27 20:02 UTC by BayleShanks
notes-cog-ai--index
* [Self:notes-cog-ai-workingMemoryAsCacheCoherency workingMemoryAsCacheCoherency] * [Self:notes-cog-ai-aiNotes . . .
3K - last updated 2021-02-27 20:02 UTC by BayleShanks
notes-cog-ai-explorationExploitation
http://en.wikipedia.org/wiki/Multi-armed_bandit#Approximate_solutions http://en.wikipedia.org/wiki/Thompson_sampling . . .
1K - last updated 2016-11-19 00:51 UTC by BayleShanks
notes-cog-ai-games
* [Self:notes-cog-ai-games-chunkingForGames chunkingForGames] * [Self:notes-cog-ai-games-go go] * [Self:notes-cog-ai-games-aiGamesMisc . . .
1K - last updated 2020-05-21 11:49 UTC by BayleShanks
notes-cog-ai-games--index
* [Self:notes-cog-ai-games-chunkingForGames chunkingForGames] * [Self:notes-cog-ai-games-go go] * [Self:notes-cog-ai-games-aiGamesMisc . . .
1K - last updated 2020-05-21 11:49 UTC by BayleShanks
notes-cog-ai-games-aiGamesMisc
the famous 'deepmind' deep learning Atari paper: [https://www.cs.toronto.edu/~vmnih/docs/dqn.pdf Playing . . .
1K - last updated 2018-08-15 10:14 UTC by BayleShanks
notes-cog-ai-games-chunkingForGames
Perhaps a good feature for a game-playing AI would be a chunking/theorem-proving module. For example, . . .
2K - last updated 2014-11-04 00:27 UTC by BayleShanks
notes-cog-ai-games-go
[http://jeffbradberry.com/posts/2015/09/intro-to-monte-carlo-tree-search/ Blog post explaining Monte . . .
3K - last updated 2015-09-15 19:47 UTC by BayleShanks
notes-cog-ai-games-misc
the famous 'deepmind' deep learning Atari paper: [https://www.cs.toronto.edu/~vmnih/docs/dqn.pdf Playing . . .
1K - last updated 2015-09-15 19:47 UTC by BayleShanks
9 pages found.