Monte Carlo Tree Search Planning for Continuous Action and State Spaces (short paper).
Federico BianchiLorenzo BonanniAlberto CastelliniAlessandro FarinelliPublished in: AIRO@AI*IA (2022)
Keyphrases
- monte carlo tree search
- continuous action
- state space
- planning problems
- monte carlo
- partially observable markov decision processes
- continuous state
- action space
- heuristic search
- markov chain
- evaluation function
- reinforcement learning methods
- reinforcement learning
- reinforcement learning algorithms
- game tree
- policy search
- real valued
- machine learning
- belief state
- domain independent
- markov decision processes
- dynamical systems
- temporal difference
- orders of magnitude
- temporal difference learning
- optimal policy
- search algorithm