Poker-AI.org

Re: Parallelisation Of CFRM-Algo Over Multiple Machines

2013-05-21T09:57:10+00:00

The Polaris paper talks about parallel implementation. You will have to combine the results every iteration. The biggest advantage IMO is the Ram of 2 machines, not a speedup.

Statistics: Posted by HontoNiBaka — Tue May 21, 2013 9:57 am

Re: Parallelisation Of CFRM-Algo Over Multiple Machines

2013-05-21T04:16:23+00:00

Ideally you would want to partition it to use the least amount of network. i.e. Splitting it at earlier branches in the game tree.

Statistics: Posted by cantina — Tue May 21, 2013 4:16 am

Re: Parallelisation Of CFRM-Algo Over Multiple Machines

2013-05-20T20:36:06+00:00

combining the regrets/strategies from two runs of n iterations is definitely not equivalent to one run of 2n iterations. i'm guessing the improvement would be marginal.

Statistics: Posted by somehomelessguy — Mon May 20, 2013 8:36 pm

Parallelisation Of CFRM-Algo Over Multiple Machines

2013-05-20T19:49:39+00:00

Hey,

how can I parallelise my chance-sampled cfrm algo over multiple machines? It's pretty obvious that data-transfer between the machines is the bottleneck. Would it work if I just run the algo for the same gametree independently on two machines and merge the regrets and strategies after n iterations?

Thx.

Statistics: Posted by iKNOWpoker — Mon May 20, 2013 7:49 pm