The Benefits of Power Regularization in Cooperative Reinforcement Learning.
Michelle LiMichael DennisPublished in: AAMAS (2023)
Keyphrases
- cooperative
- reinforcement learning
- multi agent
- multi agent reinforcement learning
- function approximation
- power consumption
- markov decision processes
- reinforcement learning algorithms
- cooperating agents
- optimal policy
- multiagent reinforcement learning
- game theory
- regularization term
- distributed problem solving
- multi agent systems
- regularization parameter
- model free
- temporal difference
- mixed norm
- markov decision process
- neural network
- parameter selection
- cooperative learning
- least squares
- state space
- evolutionary algorithm
- machine learning