Re: Monte-Carlo Tree Search as Regularized Policy Optimization
Kensuke Matsuzaki <[email protected]> Sun, 19 Jul 2020 18:30:31 +0900
| Newsgroups | gmane.games.devel.go |
|---|---|
| Message-ID | <CACLc6Sp58e+-nGp9tqitLStOrc=HAmwTVCmkTeUjFV8C6zVX+A@mail.gmail.com> |
SGksCgpJIGNvdWxkbid0IGltcHJvdmUgbGVlbGEgemVybydzIHN0cmVuZ3RoIGJ5IGltcGxlbWVu dGluZyBTRUFSQ0ggYW5kIEFDVC4KaHR0cHM6Ly9naXRodWIuY29tL3pha2tpL2xlZWxhLXplcm8v Y29tbWl0cy9yZWd1bGFyaXplZF9wb2xpY3kKCjIwMjDlubQ35pyIMTfml6Uo6YeRKSAyOjQ3IFLD qW1pIENvdWxvbSA8cmVtaS5jb3Vsb21AZ21haWwuY29tPjoKPgo+IFRoaXMgbG9va3MgdmVyeSBp bnRlcmVzdGluZy4KPgo+IEZyb20gYSBxdWljayBnbGFuY2UsIGl0IHNlZW1zIHRoZSBpbXByb3Zl bWVudCBpcyBtYWlubHkgd2hlbiB0aGUgbnVtYmVyIG9mIHBsYXlvdXRzIGlzIHNtYWxsLiBBbHNv IHRoZXkgZG9uJ3QgdGVzdCBvbiB0aGUgZ2FtZSBvZiBHby4gSGFzIGFueWJvZHkgdHJpZWQgaXQ/ Cj4KPiBJIHdpbGwgdGFrZSBhIGRlZXBlciBsb29rIGxhdGVyLgo+Cj4gT24gVGh1LCBKdWwgMTYs IDIwMjAgYXQgOTo0OSBBTSBSYXkgVGF5ZWsgPHJ0YXlla0BjYS5yci5jb20+IHdyb3RlOgo+Pgo+ PiBodHRwczovL29sZC5yZWRkaXQuY29tL3IvTWFjaGluZUxlYXJuaW5nL2NvbW1lbnRzL2hyem9v aC9yX21vbnRlY2FybG9fdHJlZV9zZWFyY2hfYXNfcmVndWxhcml6ZWRfcG9saWN5Lwo+Pgo+Pgo+ PiAtLQo+PiBIb25lc3R5IGlzIGEgdmVyeSBleHBlbnNpdmUgZ2lmdC4gU28sIGRvbid0IGV4cGVj dCBpdCBmcm9tIGNoZWFwIHBlb3BsZSAtIFdhcnJlbiBCdWZmZXR077u/Cj4+IGh0dHA6Ly90YXll ay5jb20vCj4+Cj4+IF9fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19f X19fCj4+IENvbXB1dGVyLWdvIG1haWxpbmcgbGlzdAo+PiBDb21wdXRlci1nb0Bjb21wdXRlci1n by5vcmcKPj4gaHR0cDovL2NvbXB1dGVyLWdvLm9yZy9tYWlsbWFuL2xpc3RpbmZvL2NvbXB1dGVy LWdvCj4KPiBfX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fXwo+ IENvbXB1dGVyLWdvIG1haWxpbmcgbGlzdAo+IENvbXB1dGVyLWdvQGNvbXB1dGVyLWdvLm9yZwo+ IGh0dHA6Ly9jb21wdXRlci1nby5vcmcvbWFpbG1hbi9saXN0aW5mby9jb21wdXRlci1nbwoKCgot LSAKS2Vuc3VrZSBNYXRzdXpha2kKX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19f X19fX19fX19fX18KQ29tcHV0ZXItZ28gbWFpbGluZyBsaXN0CkNvbXB1dGVyLWdvQGNvbXB1dGVy LWdvLm9yZwpodHRwOi8vY29tcHV0ZXItZ28ub3JnL21haWxtYW4vbGlzdGluZm8vY29tcHV0ZXIt Z28K