Privacy-Preserving Policy Iteration for Decentralized POMDPs.
Feng WuShlomo ZilbersteinXiaoping ChenPublished in: AAAI (2018)
Keyphrases
- privacy preserving
- policy iteration
- markov decision processes
- reinforcement learning
- policy iteration algorithm
- optimal policy
- partially observable markov decision processes
- markov decision problems
- finite state
- average reward
- model free
- privacy preserving data mining
- partially observable
- sample path
- multi agent
- vertically partitioned data
- temporal difference
- infinite horizon
- fixed point
- markov decision process
- dynamic programming
- privacy preservation
- state space
- function approximation
- data privacy
- multi party
- sensitive data
- peer to peer
- average cost
- sensitive information
- continuous state
- least squares
- horizontally partitioned data
- private information
- optimal control
- secure multiparty computation
- privacy concerns
- privacy protection
- privacy preserving association rule mining
- differential privacy
- convergence rate
- privacy sensitive
- scalar product
- np hard
- linear programming
- initial state
- learning algorithm