metadata
license: mit
tags:
- reinforcement-learning
- card-games
- estimation
Copycat
A neural network trained to copy the card choices of a look-ahead bot, so it plays similar cards far faster. The file is a NumPy .npz of the network's weights. Used by the Copycat and Copycat + look-ahead bots.
Rated on the Estimation Arena leaderboard. Code and how to run it: estimation-arena. Running it currently needs the rules engine, which is private.