MEET: A Monte Carlo Exploration-Exploitation Trade-off for Buffer Sampling.
Julius OttLorenzo ServadeiJose A. Arjona-MedinaEnrico RinaldiGianfranco MauroDaniela Sanchez LoperaMichael StephanThomas StadelmayerAvik SantraRobert WillePublished in: CoRR (2022)
Keyphrases
- monte carlo
- adaptive sampling
- importance sampling
- monte carlo simulation
- markov chain
- monte carlo methods
- particle filter
- optimal strategy
- markov chain monte carlo
- machine learning
- stochastic approximation
- simulation study
- variance reduction
- matrix inversion
- game tree
- monte carlo tree search
- markovian decision
- policy evaluation
- monte carlo method
- game tree search
- temporal difference
- least squares