One-Shot Averaging for Distributed TD (λ) Under Markov Sampling.
Haoxing TianIoannis Ch. PaschalidisAlex OlshevskyPublished in: IEEE Control. Syst. Lett. (2024)
Keyphrases
- distributed environment
- distributed systems
- markov chain
- peer to peer
- cooperative
- databases
- sampling strategies
- mobile agents
- active learning
- lightweight
- learning algorithm
- computer networks
- markov model
- communication overhead
- multi agent
- reinforcement learning
- neural network
- fault tolerant
- temporal difference
- loosely coupled
- distributed network
- data sets