Differential graphical games: Policy iteration solutions and coupled Riccati formulation.
Mohammed I. AbouheafFrank L. LewisMagdi Sadek MahmoudPublished in: ECC (2014)
Keyphrases
- policy iteration
- markov decision processes
- model free
- reinforcement learning
- optimal policy
- sample path
- average reward
- infinite horizon
- fixed point
- approximate dynamic programming
- game theory
- neural network
- least squares
- temporal difference
- markov decision process
- markov decision problems
- linear programming
- finite state
- state space
- dynamic programming
- multi agent
- policy evaluation
- learning algorithm
- machine learning