One-Shot Averaging for Distributed TD(λ) Under Markov Sampling.
Haoxing TianIoannis Ch. PaschalidisAlex OlshevskyPublished in: CoRR (2024)
Keyphrases
- distributed systems
- cooperative
- distributed environment
- markov chain
- distributed data
- multi agent
- sample size
- temporal difference
- random sampling
- database
- learning algorithm
- lightweight
- communication cost
- sampling strategy
- communication overhead
- distributed network
- loosely coupled
- semi markov
- agent technology
- fault tolerant
- mobile agents
- active learning
- reinforcement learning
- machine learning
- real time