Reinforcement Learning of Action and Query Policies with LTL Instructions under Uncertain Event Detector.
Wataru HatanakaRyota YamashinaTakamitsu MatsubaraPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- optimal policy
- database
- fitted q iteration
- data structure
- action selection
- uncertain databases
- response time
- imprecise information
- query evaluation
- partially observable domains
- transition systems
- markov decision process
- action space
- policy search
- condition action rules
- user queries
- data sources
- query processing
- model checking
- state space
- decision making
- control policy
- machine learning
- temporal logic
- incomplete information
- query expansion
- policy iteration
- initial state
- reinforcement learning algorithms
- control policies
- transition model
- model free
- function approximation
- reinforcement learning agents
- linear temporal logic
- range queries
- search engine