Reinforcement Learning of Action and Query Policies With LTL Instructions Under Uncertain Event Detector.
Wataru HatanakaRyota YamashinaTakamitsu MatsubaraPublished in: IEEE Robotics Autom. Lett. (2023)
Keyphrases
- reinforcement learning
- optimal policy
- fitted q iteration
- database
- action selection
- event detection
- markov decision process
- query processing
- policy search
- imprecise information
- response time
- action space
- query evaluation
- user queries
- condition action rules
- partially observable domains
- markov decision processes
- query expansion
- uncertain databases
- relevance feedback
- function approximation
- state space
- data sources
- reward shaping
- incomplete information
- control policies
- control policy
- temporal logic
- data structure
- partially observable markov decision processes
- markov decision problems
- temporal difference
- sufficient conditions
- keywords
- decision making
- machine learning