Athénan, a minimax-based zero-knowledge RL method without a policy, achieves 296 times lower state-data cost and at least 7 times higher speed than Polygames on multiple games.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2020 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Minimax Strikes Back
Athénan, a minimax-based zero-knowledge RL method without a policy, achieves 296 times lower state-data cost and at least 7 times higher speed than Polygames on multiple games.