A neural policy trained on 150,000 human Diplomacy games, then refined by self-play, beats rule-based bots in No Press Diplomacy.
Deepstack: Expert-level artificial intelligence in heads-up no-limit poker
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2019 1verdicts
ACCEPT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
No Press Diplomacy: Modeling Multi-Agent Gameplay
A neural policy trained on 150,000 human Diplomacy games, then refined by self-play, beats rule-based bots in No Press Diplomacy.