GPU-Accelerated Counterfactual Regret Minimization
Fuente:
arXiv
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913593080938496 |
|---|---|
| author | Kim, Juho |
| author_facet | Kim, Juho |
| contents | Counterfactual regret minimization is a family of algorithms of no-regret learning dynamics capable of solving large-scale imperfect information games. We propose implementing this algorithm as a series of dense and sparse matrix and vector operations, thereby making it highly parallelizable for a graphical processing unit, at a cost of higher memory usage. Our experiments show that our implementation performs up to about 401.2 times faster than OpenSpiel's Python implementation and, on an expanded set of games, up to about 203.6 times faster than OpenSpiel's C++ implementation and the speedup becomes more pronounced as the size of the game being solved grows. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_14778 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | GPU-Accelerated Counterfactual Regret Minimization Kim, Juho Computer Science and Game Theory Machine Learning Counterfactual regret minimization is a family of algorithms of no-regret learning dynamics capable of solving large-scale imperfect information games. We propose implementing this algorithm as a series of dense and sparse matrix and vector operations, thereby making it highly parallelizable for a graphical processing unit, at a cost of higher memory usage. Our experiments show that our implementation performs up to about 401.2 times faster than OpenSpiel's Python implementation and, on an expanded set of games, up to about 203.6 times faster than OpenSpiel's C++ implementation and the speedup becomes more pronounced as the size of the game being solved grows. |
| title | GPU-Accelerated Counterfactual Regret Minimization |
| topic | Computer Science and Game Theory Machine Learning |
| url | https://arxiv.org/abs/2408.14778 |