Privacy-Preserving Policy Synthesis in Markov Decision Processes.
Parham GohariMatthew T. HaleUfuk TopcuPublished in: CDC (2020)
Keyphrases
- privacy preserving
- markov decision processes
- optimal policy
- policy iteration
- markov decision process
- finite state
- partially observable
- average cost
- finite horizon
- average reward
- state space
- privacy preserving data mining
- infinite horizon
- action space
- state and action spaces
- reward function
- privacy preservation
- decision processes
- vertically partitioned data
- dynamic programming
- reinforcement learning
- expected reward
- decision theoretic planning
- privacy concerns
- long run
- markov decision problems
- total reward
- sensitive information
- policy evaluation
- transition matrices
- partially observable markov decision processes
- scalar product
- reinforcement learning algorithms
- record linkage
- secure multiparty computation
- continuous state spaces
- privacy sensitive
- horizontally partitioned data
- stationary policies
- data privacy
- private information
- privacy protection
- discounted reward
- differential privacy
- sensitive data
- access control
- search algorithm