Congestion-Aware Path Coordination Game With Markov Decision Process Dynamics.
Sarah H. Q. LiDaniel J. CalderoneBehçet AçikmesePublished in: IEEE Control. Syst. Lett. (2023)
Keyphrases
- markov decision process
- markov games
- state space
- multiagent reinforcement learning
- markov decision processes
- joint action
- optimal policy
- temporal difference learning
- game playing
- reinforcement learning
- infinite horizon
- dynamical systems
- finite horizon
- policy iteration
- multi agent
- game theory
- cooperative
- multiagent systems
- video games
- partial observability
- multi agent systems
- game theoretic
- initial state
- multiple agents
- reward function
- probabilistic model
- transition probabilities
- higher order
- multistage
- linear programming
- average cost
- dynamic programming
- probability distribution
- nash equilibrium
- traffic congestion
- graphical models
- mathematical model
- machine learning