Monte Carlo Matrix Inversion and Reinforcement Learning.
Andrew G. BartoMichael O. DuffPublished in: NIPS (1993)
Keyphrases
- matrix inversion
- monte carlo
- reinforcement learning
- policy evaluation
- temporal difference
- markov chain
- importance sampling
- function approximation
- reinforcement learning algorithms
- state space
- optimal policy
- monte carlo tree search
- particle filter
- markov decision processes
- learning algorithm
- variance reduction
- model free
- least squares
- function approximators
- computer graphics
- optimal control
- action selection
- computational cost
- dynamic programming