Investigating Reinforcement Learning for Communication Strategies in a Task-Initiative Setting.
Baber KhalidMatthew StonePublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- learning process
- learning algorithm
- multi agent
- state space
- neural network
- communication protocol
- optimal strategy
- function approximation
- computer networks
- software agents
- communication networks
- data acquisition
- optimal control
- machine learning
- model free
- data sets
- learning agents
- multi agent reinforcement learning
- exploration exploitation tradeoff