Measurement Simplification in ρ-POMDP with Performance Guarantees.
Tom YotamVadim IndelmanPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- genetic algorithm
- partially observable markov decision processes
- dynamical systems
- real time
- optimal policy
- finite state
- multiresolution
- partially observable
- neural network
- partially observable markov decision process
- belief space
- belief state
- state space
- lower bound
- preprocessing
- multi agent
- data acquisition
- markov chain
- model free reinforcement learning