For multiple plies I was previously using Player 2.4q as a coarse strategy to trim down the list of moves that I need to run the more expensive 0-ply evaluation on.
I've now moved that to a new coarse strategy: Player 3.2q. This is just like Player 3.2 but with five hidden nodes instead of 120 for each of the three networks.
It scores Contact ER 33.7, Crashed ER 24.8, and Race ER 2.40. Significantly stronger than Player 2.4q. (Benchmark scores updated after fix to benchmark calculation.)
In 100k cubeless money games against Player 2.4q it scores +0.210ppg +/- 0.004ppg.
I've now moved that to a new coarse strategy: Player 3.2q. This is just like Player 3.2 but with five hidden nodes instead of 120 for each of the three networks.
It scores Contact ER 33.7, Crashed ER 24.8, and Race ER 2.40. Significantly stronger than Player 2.4q. (Benchmark scores updated after fix to benchmark calculation.)
In 100k cubeless money games against Player 2.4q it scores +0.210ppg +/- 0.004ppg.
No comments:
Post a Comment