Decentralized Federated Policy Gradient with Byzantine Fault-Tolerance and Provably Fast Convergence.
Philip JordanFlorian GrötschlaFlint Xiaofeng FanRoger WattenhoferPublished in: CoRR (2024)
Keyphrases
- fault tolerance
- fault tolerant
- distributed systems
- policy gradient
- peer to peer
- load balancing
- reinforcement learning
- database replication
- actor critic
- function approximation
- fault management
- worst case
- convergence rate
- cooperative
- convergence speed
- gradient method
- mobile agents
- digital libraries
- optimal control
- approximation methods
- failure recovery
- single point of failure
- multi agent