Monte-Carlo Tree Search as Regularized Policy Optimization
Ray Tayek <[email protected]> Thu, 16 Jul 2020 00:33:15 -0700
| Newsgroups | gmane.games.devel.go |
|---|---|
| Message-ID | <[email protected]> |
aHR0cHM6Ly9vbGQucmVkZGl0LmNvbS9yL01hY2hpbmVMZWFybmluZy9jb21tZW50cy9ocnpvb2gv cl9tb250ZWNhcmxvX3RyZWVfc2VhcmNoX2FzX3JlZ3VsYXJpemVkX3BvbGljeS8KCgotLSAKSG9u ZXN0eSBpcyBhIHZlcnkgZXhwZW5zaXZlIGdpZnQuIFNvLCBkb24ndCBleHBlY3QgaXQgZnJvbSBj aGVhcCBwZW9wbGUgLSBXYXJyZW4gQnVmZmV0dO+7vwpodHRwOi8vdGF5ZWsuY29tLwoKX19fX19f X19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX18KQ29tcHV0ZXItZ28gbWFp bGluZyBsaXN0CkNvbXB1dGVyLWdvQGNvbXB1dGVyLWdvLm9yZwpodHRwOi8vY29tcHV0ZXItZ28u b3JnL21haWxtYW4vbGlzdGluZm8vY29tcHV0ZXItZ28K