Receding-horizon planning using recursive Monte Carlo Tree Search with Sparse Action Sampling for continuous state and action spaces.
Moritz SchneiderPublished in: ACC (2016)
Keyphrases
- monte carlo tree search
- monte carlo
- receding horizon
- action selection
- evaluation function
- temporal difference
- markov chain
- neural network
- image classification
- planning problems
- optimal strategy
- sparse approximation
- temporal difference learning
- action space
- initial state
- game tree
- planning domains
- sparse coding
- sparse representation
- search space
- support vector
- machine learning