Primal-Dual Algorithm for Distributed Reinforcement Learning: Distributed GTD.
Donghwan LeeHyung-Jin YoonNaira HovakimyanPublished in: CDC (2018)
Keyphrases
- reinforcement learning
- multi agent
- lightweight
- distributed environment
- communication cost
- databases
- data mining
- real time
- peer to peer networks
- state space
- computer networks
- fault tolerant
- distributed learning
- distributed processing
- loosely coupled
- agent technology
- intelligent agents
- decision making
- learning algorithm
- information retrieval
- data sets