Resilient Mechanism Against Byzantine Failure for Distributed Deep Reinforcement Learning.
Mingyue ZhangZhi JinJian HouRenwei LuoPublished in: ISSRE (2022)
Keyphrases
- reinforcement learning
- fault tolerant
- distributed systems
- multi agent
- distributed environment
- selection mechanism
- failure prediction
- distributed data
- optimal policy
- markov decision processes
- peer to peer
- state space
- function approximation
- dynamic programming
- cooperative
- machine learning
- computer networks
- agent technology
- model free
- communication overhead
- failure rate
- control policy