Influence of State-Variable Constraints on Partially Observable Monte Carlo Planning.
Alberto CastelliniGeorgios ChalkiadakisAlessandro FarinelliPublished in: IJCAI (2019)
Keyphrases
- monte carlo
- partially observable
- state variables
- state space
- markov chain
- particle filter
- markov decision processes
- dynamical systems
- reinforcement learning
- heuristic search
- reward function
- partial observability
- planning problems
- decision problems
- dynamic systems
- markov decision problems
- belief state
- dynamic programming
- orders of magnitude
- transition probabilities
- reinforcement learning algorithms
- monte carlo tree search
- infinite horizon
- planning domains
- optimal policy
- causal graph
- visual tracking
- markov decision process
- optimal control
- random variables
- classical planning
- search space
- multi agent systems
- search algorithm