Offline Reinforcement Learning with Generative Adversarial Networks and Uncertainty Estimation.
Lan WuQuan LiuLihua ZhangZhigang HuangPublished in: ICASSP (2024)
Keyphrases
- reinforcement learning
- multi agent
- partial observability
- learning algorithm
- social networks
- function approximation
- accurate estimation
- network design
- estimation algorithm
- network structure
- network size
- discriminative learning
- state space
- reinforcement learning algorithms
- temporal difference
- data driven
- markov decision processes
- unsupervised learning
- estimation error
- real time
- expected utility
- heterogeneous networks
- uncertain data
- computer networks
- estimation accuracy
- robust optimization
- complex networks
- data mining