Markov Games with Decoupled Dynamics: Price of Anarchy and Sample Complexity.
Runyu ZhangYuyang ZhangRohit KondaBryce R. FergusonJason R. MardenNa LiPublished in: CDC (2023)
Keyphrases
- sample complexity
- markov games
- theoretical analysis
- learning problems
- reinforcement learning algorithms
- special case
- upper bound
- active learning
- reinforcement learning
- learning algorithm
- multiagent reinforcement learning
- pac learning
- markov decision processes
- vc dimension
- lower bound
- supervised learning
- generalization error
- markov decision process
- sample size
- dynamical systems
- multiagent systems
- learning tasks
- search space
- control problems
- multi agent
- cooperative
- training examples
- state space
- optimal solution
- cross validation
- model selection
- stochastic games
- data sets