An Accelerated Multi-level Monte Carlo Approach for Average Reward Reinforcement Learning with General Policy Parametrization.
Swetha GaneshVaneet AggarwalPublished in: CoRR (2024)
Keyphrases
- monte carlo
- average reward reinforcement learning
- markov chain
- monte carlo simulation
- optimal policy
- monte carlo tree search
- conditional density estimation
- adaptive sampling
- importance sampling
- markovian decision
- monte carlo methods
- policy evaluation
- simulation study
- particle filter
- matrix inversion
- point processes
- stochastic approximation
- variance reduction
- optimal strategy
- model selection
- kernel methods
- reinforcement learning