On MABs and Separation of Concerns in Monte-Carlo Planning for MDPs.
Zohar FeldmanCarmel DomshlakPublished in: ICAPS (2014)
Keyphrases
- monte carlo
- multi agent based simulation
- policy evaluation
- markov decision processes
- planning problems
- social simulation
- markov chain
- state space
- importance sampling
- monte carlo simulation
- particle filter
- monte carlo methods
- markov decision problems
- markovian decision
- temporal difference
- adaptive sampling
- monte carlo tree search
- initial state
- reinforcement learning
- dynamic programming
- matrix inversion
- variance reduction
- partially observable
- game tree
- optimal strategy
- optimal policy
- least squares