Mitigating Metastable Failures in Distributed Systems with Offline Reinforcement Learning.
Yueying LiDaochen ZhaTianjun ZhangG. Edward SuhChristina DelimitrouFrancis Y. YanPublished in: Tiny Papers @ ICLR (2023)
Keyphrases
- distributed systems
- reinforcement learning
- distributed environment
- function approximation
- load balancing
- message passing
- fault tolerant
- geographically distributed
- reinforcement learning algorithms
- distributed computing
- distributed database systems
- fault tolerance
- data replication
- security policies
- learning algorithm
- loosely coupled
- mobile agents
- state space
- real time
- agent based systems
- concurrent systems
- operating system
- risk management
- software engineering
- mobile robot
- multi agent
- database systems
- replicated data