Monte-Carlo Planning and Learning with Language Action Value Estimates.
Youngsoo JangSeokin SeoJongmin LeeKee-Eung KimPublished in: ICLR (2021)
Keyphrases
- monte carlo
- importance sampling
- markov chain
- markovian decision
- action selection
- learning process
- learning tasks
- monte carlo method
- monte carlo methods
- monte carlo tree search
- monte carlo simulation
- temporal difference
- reinforcement learning
- variance reduction
- temporal difference learning
- stochastic approximation
- adaptive sampling
- learning algorithm