The Benefits of Power Regularization in Cooperative Reinforcement Learning.
Michelle LiMichael DennisPublished in: CoRR (2024)
Keyphrases
- cooperative
- reinforcement learning
- multi agent reinforcement learning
- multi agent
- power consumption
- function approximation
- model free
- game theory
- multiagent reinforcement learning
- cooperative learning
- supervised learning
- multi agent systems
- learning algorithm
- markov decision processes
- state space
- temporal difference
- parameter selection
- reinforcement learning algorithms
- solve complex tasks
- machine learning
- robotic control
- transition model
- temporal difference learning
- regularization term
- regularization parameter