Computing the Lp-strong nash equilibrium looking for cooperative stability in multiple agents markov games.
Kristal K. TrejoJulio B. ClempnerAlexander S. PoznyakPublished in: CCE (2015)
Keyphrases
- multiple agents
- markov games
- nash equilibrium
- multiagent reinforcement learning
- cooperative
- multi agent
- game theory
- stochastic games
- single agent
- game theoretic
- linear programming
- multi agent systems
- multiagent systems
- reinforcement learning algorithms
- nash equilibria
- reinforcement learning
- markov decision processes
- control problems
- reward function
- equilibrium strategies
- mixed strategy
- worst case
- machine learning
- path planning
- learning algorithm