Rule-based Shield Synthesis for Partially Observable Monte Carlo Planning.
Giulio MazziAlberto CastelliniAlessandro FarinelliPublished in: OVERLAY@GandALF (2021)
Keyphrases
- monte carlo
- partially observable
- state space
- decision problems
- markov decision processes
- reinforcement learning
- dynamical systems
- partial observability
- markov chain
- markov decision problems
- planning domains
- belief space
- importance sampling
- partial observations
- infinite horizon
- monte carlo simulation
- belief state
- particle filter
- monte carlo tree search
- planning problems
- reward function
- partially observable markov decision processes
- optimal strategy
- ai planning
- heuristic search
- linear programming
- least squares