Monotonic Quantile Network for Worst-Case Offline Reinforcement Learning.
Chenjia BaiTing XiaoZhoufan ZhuLingxiao WangFan ZhouAnimesh GargBin HePeng LiuZhaoran WangPublished in: IEEE Trans. Neural Networks Learn. Syst. (2024)
Keyphrases
- reinforcement learning
- worst case
- computer networks
- network model
- function approximation
- network traffic
- upper bound
- dynamic programming
- markov decision processes
- complex networks
- lower bound
- network architecture
- real time
- communication networks
- approximation algorithms
- optimal policy
- artificial neural networks
- error bounds
- computational complexity
- network design
- temporal difference
- network topologies