Joscha Bach Retweeted Shawn Presser
GPT-2 learns a deep but not a fully integrated model. It can learn to play chess, but will make invalid moves (which can be fixed by filtering them out). After a number of moves, it apparently forgets its context. Could it be combined with a coherent working memory?https://twitter.com/theshawwn/status/1213559429293060099 …
Joscha Bach added,
Shawn Presser @theshawwn
GPT2 Chess update: I wrote some code to calculate the probability of all valid chess moves. It can reach endgame now. https://lichess.org/UMyang4z
It starts to blunder every game at around move 13. We suspect it’s losing track of board state. (It’s trained solely on PGN notation.)
Show this thread
4:52 PM - 7 Jan 2020
0 replies
2 retweets
5 likes
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.