SARSA(0) Reinforcement Learning over Fully Homomorphic Encryption.
Jihoon SuhTakashi TanakaPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- homomorphic encryption
- function approximation
- reinforcement learning algorithms
- temporal difference learning
- privacy preserving
- function approximators
- temporal difference
- state space
- action selection
- data sharing
- optimal policy
- markov decision processes
- rl algorithms
- model free
- learning algorithm
- end users
- public key
- encryption scheme