Determining Optimal Incentive Policy for Decentralized Distributed Systems Using Reinforcement Learning.
Elitsa PankovskaAshish Rajendra SaiHarald VrankenPublished in: ICBC (2023)
Keyphrases
- distributed systems
- reinforcement learning
- control policy
- fault tolerant
- optimal policy
- control policies
- fault tolerance
- distributed environment
- markov decision process
- distributed database systems
- mobile agents
- load balancing
- concurrent systems
- real time systems
- distributed computing
- optimal control
- multi agent
- operating system
- average reward
- policy search
- dynamic programming
- markov decision processes
- data replication
- loosely coupled
- policy iteration
- action space
- deadlock detection
- geographically distributed
- function approximators
- partially observable
- reward function
- action selection
- function approximation
- state space
- mobile robot
- data availability
- continuous state
- policy gradient
- cooperative