GoudaGame commited on
Commit
ef32a7b
·
verified ·
1 Parent(s): 269b6f9

Update the model card

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -8,6 +8,6 @@ tags:
8
 
9
  # Self-taught
10
 
11
- Plays Estimation with one neural network for every decision, bids and cards alike. It learned from nothing by playing itself, rewarded for where it finished at the table. The file is a NumPy `.npz` of the network's weights. Used by the Self-taught and Self-taught + look-ahead bots.
12
 
13
  Rated on the [Estimation Arena leaderboard](https://essamgouda97.github.io/estimation-arena/). Code and how to run it: [estimation-arena](https://github.com/essamgouda97/estimation-arena). Running it currently needs the rules engine, which is private.
 
8
 
9
  # Self-taught
10
 
11
+ Plays Estimation with one neural network for every decision, bids and cards alike. It learned from nothing by playing itself, rewarded for where it finished at the table: first whole games, then the five-round games the leaderboard plays. The file also holds a small second network that learned, from the same games, where a seat is likely to finish given the scores so far; the look-ahead bots use it to judge a round by what it does to the game. The file is a NumPy `.npz` of the network's weights. Used by the Self-taught, Self-taught + look-ahead and Self-taught + guesses bots.
12
 
13
  Rated on the [Estimation Arena leaderboard](https://essamgouda97.github.io/estimation-arena/). Code and how to run it: [estimation-arena](https://github.com/essamgouda97/estimation-arena). Running it currently needs the rules engine, which is private.