Against count-based learners in repeated games, the optimal deceptive sequence is computable by dynamic programming in small cases, approximable in larger ones, but NP-hard to approximate against ERM even in zero-sum games.
Title resolution pending
1 Pith paper cite this work, alongside 49 external citations. Polarity classification is still indexing.
1
Pith paper citing it
49
external citations · OpenAlex
fields
cs.GT 1years
2026 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
On the Power of Deception in Repeated Games
Against count-based learners in repeated games, the optimal deceptive sequence is computable by dynamic programming in small cases, approximable in larger ones, but NP-hard to approximate against ERM even in zero-sum games.