Monte Carlo Tree Search Guided by Symbolic Advice for MDPs.
Damien Busatto-GastonDebraj ChakrabortyJean-François RaskinPublished in: CONCUR (2020)
Keyphrases
- monte carlo tree search
- bayesian reinforcement learning
- monte carlo
- markov decision processes
- tree search algorithm
- evaluation function
- reinforcement learning
- optimal policy
- state space
- temporal difference
- monte carlo search
- game tree
- reinforcement learning methods
- policy iteration
- temporal difference learning
- markov decision process
- learning algorithm
- neural network
- binary decision diagrams
- initial state
- reward function
- decision problems
- particle filter