Computational Performance of Deep Reinforcement Learning to find Nash Equilibria.
Christoph GrafViktor ZobernigJohannes SchmidtClaude KlöcklPublished in: CoRR (2021)
Keyphrases
- nash equilibria
- reinforcement learning
- incomplete information
- multiagent learning
- game theory
- stochastic games
- fictitious play
- game theoretic
- nash equilibrium
- function approximation
- pure strategy
- markov decision processes
- state space
- multi agent reinforcement learning
- mathematical programming
- cost function
- model free
- special case
- policy iteration
- multi agent
- machine learning
- artificial intelligence
- multi agent learning
- solution concepts
- search space
- optimal control
- mobile robot
- resource allocation