Neural Network Ensembles in Reinforcement Learning.
Stefan FaußerFriedhelm SchwenkerPublished in: Neural Process. Lett. (2015)
Keyphrases
- neural network ensembles
- reinforcement learning
- function approximation
- state space
- neural network
- optimal policy
- markov decision processes
- reinforcement learning algorithms
- model free
- multi agent
- learning algorithm
- continuous state
- action selection
- temporal difference
- robot control
- fitted q iteration
- case study
- direct policy search
- databases
- multi agent reinforcement learning
- stochastic approximation
- learning agents
- partially observable
- data mining
- dynamic programming
- optimal solution
- decision making
- multiscale