Conditions for the convergence of one-layer networks under reinforcement learning.
J. C. C. IpMabo Robert ItoP. D. LawrencePublished in: IJCNN (1990)
Keyphrases
- reinforcement learning
- stochastic approximation
- initial conditions
- convergence rate
- function approximation
- sufficient conditions
- multi agent
- dynamic programming
- state space
- optimal policy
- markov decision processes
- neural network
- optimal control
- network analysis
- learning classifier systems
- computer networks
- multi agent reinforcement learning
- network model
- community detection
- monte carlo
- social networks
- machine learning