Application of the LSPI reinforcement learning technique to a co-located network negotiation problem.
Milos RovcaninPublished in: WOWMOM (2013)
Keyphrases
- reinforcement learning
- model free
- reinforcement learning algorithms
- temporal difference
- markov decision processes
- function approximation
- policy iteration
- reinforcement learning methods
- optimal policy
- state space
- multi agent
- supervised learning
- dynamic programming
- decision making
- control problems
- learning algorithm
- state action
- neural network