Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo.
Haque IshfaqQingfeng LanPan XuA. Rupam MahmoodDoina PrecupAnima AnandkumarKamyar AzizzadenesheliPublished in: CoRR (2023)
Keyphrases
- monte carlo
- reinforcement learning
- temporal difference
- stochastic approximation
- monte carlo simulation
- importance sampling
- monte carlo tree search
- monte carlo methods
- policy evaluation
- markov chain
- particle filter
- adaptive sampling
- markovian decision
- simulation study
- function approximation
- temporal difference learning
- optimal strategy
- matrix inversion
- point processes
- state space
- function approximators
- monte carlo method
- reinforcement learning algorithms
- optimal policy
- quasi monte carlo