Using temporal-difference learning for multi-agent bargaining.
Shiu-li HuangFu-ren LinPublished in: Electron. Commer. Res. Appl. (2008)
Keyphrases
- temporal difference learning
- multi agent
- reinforcement learning
- coalition formation
- function approximation
- fixed point
- evaluation function
- game playing
- temporal difference
- approximate value iteration
- reinforcement learning algorithms
- utility function
- markov decision process
- multi agent systems
- multiple agents
- single agent
- dynamic programming
- model free
- state space
- policy iteration
- function approximators
- regression model
- artificial neural networks
- reward function