Adaptive learning in two-player Stackelberg games with continuous action sets.
Guosong YangRadha PoovendranJoão P. HespanhaPublished in: CDC (2019)
Keyphrases
- adaptive learning
- action sets
- reinforcement learning
- nash equilibria
- reinforcement learning algorithms
- markov decision processes
- nash equilibrium
- finite state
- state space
- action space
- game theoretic
- game theory
- incomplete information
- function approximation
- optimal policy
- model free
- learning objects
- learning environment
- single agent
- learning algorithm
- learning resources
- learning activities
- average cost
- perfect information
- stationary policies
- student model
- sufficient conditions
- supply chain
- learning process
- multi agent
- data mining
- leader follower