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