Byzantine-Resilient Decentralized TD Learning with Linear Function Approximation.
Zhaoxian WuHan ShenTianyi ChenQing LingPublished in: ICASSP (2021)
Keyphrases
- function approximation
- td learning
- temporal difference
- temporal difference learning algorithms
- function approximators
- reinforcement learning
- model free
- learning tasks
- td methods
- radial basis function
- evaluation function
- multi agent
- reinforcement learning algorithms
- policy evaluation
- reinforcement learning problems
- feature extraction
- decision trees
- e learning
- machine learning