Monte Carlo Value Iteration with Macro-Actions.
Zhan Wei LimDavid HsuWee Sun LeePublished in: NIPS (2011)
Keyphrases
- monte carlo
- macro actions
- markov decision processes
- state space
- markov chain
- particle filter
- reinforcement learning
- optimal policy
- finite state
- policy iteration
- dynamic programming
- monte carlo simulation
- heuristic search
- monte carlo tree search
- partially observable
- planning under uncertainty
- markov decision process
- reinforcement learning algorithms
- average reward
- average cost
- optimal strategy
- reward function
- temporal difference
- infinite horizon
- variance reduction
- decision theoretic planning
- machine learning
- quasi monte carlo
- action space
- belief state
- dynamical systems
- orders of magnitude
- search algorithm
- genetic algorithm