Multi-agent Policy Optimization with Approximatively Synchronous Advantage Estimation.
Lipeng WanXuwei SongXuguang LanNanning ZhengPublished in: CoRR (2020)
Keyphrases
- multi agent
- optimization problems
- global optimization
- cooperative
- optimization algorithm
- neural network
- estimation accuracy
- accurate estimation
- reinforcement learning
- markov random field
- parameter estimation
- optimization process
- estimation algorithm
- partially observable markov decision processes
- data sets
- action selection
- multiple agents
- optimization methods
- multiagent systems