首页 > 其他分享 >读论文《IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures》——(续)实

读论文《IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures》——(续)实

时间:2022-10-11 21:13:27浏览次数:88  
标签:Weighted Importance 论文 Learner Scalable Actor Architectures

论文地址:

https://arxiv.org/pdf/1802.01561v2.pdf

 

 

 

论文《IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures》是基于论文《Safe and efficient off-policy reinforcement learning》改进后的分布式版本,基础论文《Safe and efficient off-policy reinforcement learning》的地址为:

https://arxiv.org/pdf/1606.02647.pdf

 

 

相关资料:

Deepmind Lab环境的python扩展库的安装:

https://www.cnblogs.com/devilmaycry812839668/p/16750126.html

 

 

 

读论文《IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures》

 

 

=========================================

 

 

官方的代码地址:(现已无法运行

https://gitee.com/devilmaycry812839668/scalable_agent

需要注意的一点是这个offical的代码由于多年无人维护,现在已经无法运行,只做留档之用。

 

 

=========================================

标签:Weighted,Importance,论文,Learner,Scalable,Actor,Architectures
From: https://www.cnblogs.com/devilmaycry812839668/p/16782564.html

相关文章