activity
19982025
most citedThe Optimal Reward Baseline for Gradient-Based Reinforcement Learning

160 citations · 222 across the 3 of their papers we have counts for

collaborators
Showing 1998 · cs.NEShow all

1 paper · 2 filters

cs.NE1998

Evolution of Neural Networks to Play the Game of Dots-and-Boxes

Lex Weaver, Terry Bossomaier

Dots-and-Boxes is a child's game which remains analytically unsolved. We implement and evolve artificial neural networks to play this game, evaluating them against simple heuristic…