Deriving an optimally deceptive policy in two-player iterated games.
Elisabeth PaulsonBooz Allen HamiltonChristopher GriffinPublished in: ACC (2016)
Keyphrases
- nash equilibria
- perfect information
- nash equilibrium
- game theoretic
- learning agents
- imperfect information
- repeated games
- game theory
- game playing
- stochastic games
- multi player
- incomplete information
- game play
- solution concepts
- optimal policy
- video games
- computer games
- markov decision processes
- infinite horizon
- game design
- policy iteration
- average reward
- decision making
- deception detection
- board game
- asymptotically optimal
- educational games
- dynamic programming