Blackwell Optimality in stochastic Games.
Vikas Vikram SinghN. HemachandraK. S. Mallikarjuna RaoPublished in: IGTR (2013)
Keyphrases
- stochastic games
- average reward
- markov decision processes
- games with incomplete information
- multiagent reinforcement learning
- nash equilibria
- optimal policy
- learning automata
- optimal solution
- long run
- multi agent
- imperfect information
- reinforcement learning
- single agent
- robust optimization
- reinforcement learning algorithms
- policy iteration
- markov chain
- average cost
- learning agent
- multistage
- dynamic environments
- repeated games
- lower bound
- learning algorithm