Joint Equilibrium Policy Search for Multi-Agent Scheduling Problems.
Thomas GabelMartin A. RiedmillerPublished in: MATES (2008)
Keyphrases
- policy search
- scheduling problem
- multi agent
- reinforcement learning
- continuous state
- partially observable markov decision processes
- reinforcement learning algorithms
- dynamic programming
- multi agent systems
- flowshop
- game theory
- nash equilibrium
- state space
- np hard
- model free
- temporal difference
- single agent
- optimal policy
- markov decision processes
- function approximation
- reward function
- linear programming