Optimizing Expectation with Guarantees in POMDPs.
Krishnendu ChatterjeePetr NovotnýGuillermo A. PérezJean-François RaskinDorde ZikelicPublished in: AAAI (2017)
Keyphrases
- reinforcement learning
- partially observable markov decision processes
- belief state
- dynamic programming
- partially observable
- information retrieval
- state space
- initial state
- neural network
- distributed constraint optimization
- mobile robot
- probability distribution
- optimal policy
- markov decision processes
- partial observability
- policy search