Difference Advantage Estimation for Multi-Agent Policy Gradients.
Yueheng LiGuangming XieZongqing LuPublished in: ICML (2022)
Keyphrases
- multi agent
- cooperative
- multi agent systems
- estimation algorithm
- neural network
- estimation accuracy
- intelligent agents
- accurate estimation
- traffic signal control
- data sets
- partially observable markov decision processes
- agent oriented
- reward function
- parameter estimation
- reinforcement learning
- information systems
- machine learning