An opponent-aware Q-learning scheme, built on level-k reasoning and Bayesian averaging over adversary types, improves robustness and exploitability in security games and repeated matrix games.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Opponent Aware Reinforcement Learning
An opponent-aware Q-learning scheme, built on level-k reasoning and Bayesian averaging over adversary types, improves robustness and exploitability in security games and repeated matrix games.