Super human Stratego with RL and test time search

Super human Stratego with RL and test time search(arxiv.org)

2 points by algo_trader 182 days ago | 1 comment

algo_trader 182 days ago |

Only 2000 GPU hours Heavily customized network 95% win rate in recent human tournament sample Several training techniques for evaluation/learning rate

algo_trader 182 days ago |

Only 2000 GPU hours Heavily customized network 95% win rate in recent human tournament sample Several training techniques for evaluation/learning rate