Stationary Anonymous Sequential Games with Undiscounted Rewards.
Piotr WiecekEitan AltmanPublished in: J. Optim. Theory Appl. (2015)
Keyphrases
- markov decision processes
- stochastic games
- non stationary
- nash equilibria
- reinforcement learning
- computer games
- video games
- policy iteration
- multiarmed bandit
- average reward
- game design
- reinforcement learning algorithms
- human computation
- infinite horizon
- digital games
- game playing
- game play
- nash equilibrium
- peer to peer
- educational games
- imperfect information
- coalitional games
- markov decision problems
- board game
- stationary policies
- total reward
- dynamic programming