Truncating Trajectories in Monte Carlo Reinforcement Learning.
Riccardo PoianiAlberto Maria MetelliMarcello RestelliPublished in: CoRR (2023)
Keyphrases
- monte carlo
- reinforcement learning
- temporal difference
- stochastic approximation
- markov chain
- temporal difference learning
- policy evaluation
- monte carlo simulation
- function approximation
- importance sampling
- state space
- adaptive sampling
- monte carlo tree search
- simulation study
- monte carlo methods
- moving objects
- point processes
- learning algorithm
- markovian decision
- optimal strategy
- variance reduction
- reinforcement learning algorithms
- function approximators
- model free
- confidence intervals
- markov decision processes
- particle filter
- dynamic programming
- matrix inversion
- control strategies
- monte carlo method
- reinforcement learning methods
- markov decision process
- optimal control
- image sequences