Collaboration between MAC Policies and IDS based on a Meta-Policy approach.
Mathieu BlancJérémy BriffautJean-François LalandeChristian ToinardPublished in: CTS (2006)
Keyphrases
- optimal policy
- policy making
- control policies
- management policies
- markov decision process
- access control policies
- transport systems
- policy search
- policy gradient methods
- revenue management
- intrusion detection system
- allocation policies
- allocation policy
- control policy
- markov decision processes
- decision processes
- state space
- markov decision problems
- reinforcement learning
- privacy policies
- intrusion detection
- decision problems
- dynamic programming
- information sharing
- meta level
- finite horizon
- long run
- average reward
- scheduling policies
- infinite horizon
- optimal production
- knowledge management
- total reward
- partially observable markov decision processes
- collaborative learning
- asymptotically optimal
- access control
- reward function
- state dependent
- selective perception
- knowledge sharing
- anomaly detection
- expected reward
- partially observable
- open government
- conflict resolution
- natural actor critic