Monte Carlo Tree Search guided by Symbolic Advice for MDPs.
Damien Busatto-GastonDebraj ChakrabortyGilles GeeraertsJean-François RaskinPublished in: CoRR (2020)
Keyphrases
- monte carlo tree search
- monte carlo
- bayesian reinforcement learning
- markov decision processes
- tree search algorithm
- reinforcement learning
- evaluation function
- reinforcement learning methods
- optimal policy
- monte carlo search
- temporal difference
- reinforcement learning algorithms
- initial state
- game tree
- average cost
- alpha beta search
- markov chain
- state space
- finite state
- learning algorithm
- infinite horizon
- transition probabilities
- average reward
- branch and bound
- sufficient conditions
- dynamic programming