Beam Search

Reported on 1 benchmark across 1 task · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Playing Games1 result

Playing the Game of 2048onThe Game of 2048
Average Score· 2021-10-20
1024
best: 500000 (Stochastic Muzero)
SOTA
Playing 2048 With Reinforcement Learning arXiv:2110.10374