admin管理员组

文章数量:1130349

原文：https://deepmind/blog/alphastar-mastering-real-time-strategy-game-starcraft-ii

 

SL = supervised learning, RL = reinforcement learning

 

  • how AlphaStar is trained

units, properties -> DNN -> instructions

DNN: transform torso(relational deep RL), deep LSTM core, auto-regressive policy head with pointer network, centralised value baseline

train: SL -> mico/macro strategies

        compete -> hyper parameters updated by RL -> Nash distribution -> final agent

multi-agent RL: play against each other: population-based, multi-agent RL -> huge strategic space -> defeat strongest and eariler ones

 

explore new build orders, unit compositions, micro-management plans

personal objective: beat specific competitor/beat distribution of competitors/building more of specific unit

NN weights: off-policy actor-critic RL with experience replay, self-imitation learning, policy distillation

 

run on TPUs, final agent: Nash distribution of the league: best mixture of strategies

 

  • how AlphaStar plays and how to evaluate

TLO/MaNa  ~ 100 APM

agent  ~ 1000, 10000 APM

AlphaStar vs. TLO/MaNa  ~280 APM (read screen frames use raw interface)

AlphaStar act: observation -> action: 350ms/avg, process every frame

results: 5:0

 

转载于:https://wwwblogs/yaoyaohust/p/10815039.html

原文：https://deepmind/blog/alphastar-mastering-real-time-strategy-game-starcraft-ii

 

SL = supervised learning, RL = reinforcement learning

 

  • how AlphaStar is trained

units, properties -> DNN -> instructions

DNN: transform torso(relational deep RL), deep LSTM core, auto-regressive policy head with pointer network, centralised value baseline

train: SL -> mico/macro strategies

        compete -> hyper parameters updated by RL -> Nash distribution -> final agent

multi-agent RL: play against each other: population-based, multi-agent RL -> huge strategic space -> defeat strongest and eariler ones

 

explore new build orders, unit compositions, micro-management plans

personal objective: beat specific competitor/beat distribution of competitors/building more of specific unit

NN weights: off-policy actor-critic RL with experience replay, self-imitation learning, policy distillation

 

run on TPUs, final agent: Nash distribution of the league: best mixture of strategies

 

  • how AlphaStar plays and how to evaluate

TLO/MaNa  ~ 100 APM

agent  ~ 1000, 10000 APM

AlphaStar vs. TLO/MaNa  ~280 APM (read screen frames use raw interface)

AlphaStar act: observation -> action: 350ms/avg, process every frame

results: 5:0

 

转载于:https://wwwblogs/yaoyaohust/p/10815039.html

本文标签： 博客RealTimeAlphaStarMastering

版权声明：本文标题：AlphaStar: Mastering the Real-Time Strategy Game StarCraft II 博客阅读 内容由热心网友自发贡献，该文观点仅代表作者本人， 转载请联系作者并注明出处：https://it.en369.cn/jiaocheng/1754916713a2741357.html， 本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如发现本站有涉嫌抄袭侵权/违法违规的内容，一经查实，本站将立刻删除。