| Poker-AI.org http://poker-ai.org/phpbb/ |
|
| Parallelisation Of CFRM-Algo Over Multiple Machines http://poker-ai.org/phpbb/viewtopic.php?f=24&t=2496 |
Page 1 of 1 |
| Author: | iKNOWpoker [ Mon May 20, 2013 7:49 pm ] |
| Post subject: | Parallelisation Of CFRM-Algo Over Multiple Machines |
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. |
|
| Author: | somehomelessguy [ Mon May 20, 2013 8:36 pm ] |
| Post subject: | Re: Parallelisation Of CFRM-Algo Over Multiple Machines |
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. |
|
| Author: | cantina [ Tue May 21, 2013 4:16 am ] |
| Post subject: | Re: Parallelisation Of CFRM-Algo Over Multiple Machines |
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. |
|
| Author: | HontoNiBaka [ Tue May 21, 2013 9:57 am ] |
| Post subject: | Re: Parallelisation Of CFRM-Algo Over Multiple Machines |
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. |
|
| Page 1 of 1 | All times are UTC |
| Powered by phpBB® Forum Software © phpBB Group http://www.phpbb.com/ |
|