Towards the Specification of Natural Language Accountability Policies with AccLab: The Laptop Policy Use Case.
Walid BenghabritJean-Claude RoyerAnderson Santana de OliveiraPublished in: CARe-MAS@PRIMA (2017)
Keyphrases
- optimal policy
- natural language
- access control policies
- formal language
- management policies
- control policies
- markov decision process
- policy search
- transport systems
- conflict resolution
- access control
- revenue management
- allocation policies
- markov decision processes
- allocation policy
- decision processes
- policy gradient methods
- state space
- control policy
- knowledge representation
- scheduling policies
- privacy policies
- dynamic programming
- language processing
- high level
- machine learning
- natural language processing
- formal languages
- natural language interface
- markov decision problems
- selective perception
- expected reward
- question answering
- long run
- partially observable markov decision processes
- reward function
- infinite horizon
- semantic interpretation
- reinforcement learning
- optimal pricing
- requirements analysis
- state dependent
- sufficient conditions
- natural language generation
- finite horizon
- optimal production
- asymptotically optimal
- semantic analysis
- security policies
- supply chain
- total reward
- approximate policy iteration
- average reward
- activity diagrams
- lost sales