Differentiable Multi-Agent Actor-Critic for Multi-Step Radiology Report Summarization.
Sanjeev Kumar KarnNing LiuHinrich SchützeOladimeji FarriPublished in: ACL (1) (2022)
Keyphrases
- multi step
- multi agent
- actor critic
- reinforcement learning
- policy gradient
- function approximation
- temporal difference
- neuro fuzzy
- reinforcement learning algorithms
- k nearest neighbor
- knn
- neural network
- approximate dynamic programming
- multi agent systems
- optimal control
- policy iteration
- loss function
- monte carlo
- least squares
- single agent
- machine learning
- linear combination
- reward function