Markov Games with Decoupled Dynamics: Price of Anarchy and Sample Complexity.
Runyu ZhangYuyang ZhangRohit KondaBryce L. FergusonJason R. MardenNa LiPublished in: CoRR (2023)
Keyphrases
- sample complexity
- markov games
- theoretical analysis
- learning problems
- markov decision processes
- upper bound
- pac learning
- learning algorithm
- special case
- multiagent reinforcement learning
- generalization error
- vc dimension
- lower bound
- reinforcement learning algorithms
- active learning
- reinforcement learning
- supervised learning
- markov decision process
- training examples
- dynamical systems
- learning tasks
- sample size
- multi agent
- control problems
- machine learning algorithms
- semi supervised learning
- small number
- machine learning
- multiagent systems
- cross validation
- cooperative
- nash equilibrium
- worst case
- average case
- training data
- semi supervised
- training set