Keyphrases
- reinforcement learning
- multi agent
- distributed systems
- state space
- cooperative
- function approximation
- computer networks
- markov decision processes
- multi agent reinforcement learning
- distributed network
- communication overhead
- distributed computing
- highly efficient
- fault tolerant
- dynamic programming
- database
- lightweight
- evaluation function
- peer to peer
- optimal control
- learning process
- distributed data
- model free
- search space
- distributed architecture
- genetic algorithm
- neural network