Faster Hamiltonian Monte Carlo by Learning Leapfrog Scale.
Changye WuJulien StoehrChristian P. RobertPublished in: CoRR (2018)
Keyphrases
- monte carlo
- markovian decision
- reinforcement learning
- monte carlo simulation
- learning process
- learning tasks
- importance sampling
- markov chain
- learning algorithm
- state space
- probability distribution
- simulation study
- action selection
- temporal difference
- temporal difference learning
- stochastic approximation
- matrix inversion