Utility-Based Reinforcement Learning for Reactive Grids.
Julien PerezCécile Germain-RenaudBalázs KéglCharles LoomisPublished in: ICAC (2008)
Keyphrases
- reinforcement learning
- function approximation
- state space
- multi agent
- machine learning
- learning algorithm
- reinforcement learning algorithms
- grid computing
- learning process
- markov decision processes
- agent architecture
- genetic algorithm
- reactive agents
- multi agent reinforcement learning
- reinforcement learning methods
- robot control
- optimal policy
- supervised learning
- dynamic programming
- model free
- reward function
- utility function
- temporal difference learning
- stochastic approximation
- autonomous learning
- grid points
- multi agent systems
- robotic control