Teamwork Reinforcement Learning With Concave Utilities.
Zheng YuJunyu ZhangZheng WenAndrea TacchettiMengdi WangIan GempPublished in: IEEE Trans. Mob. Comput. (2024)
Keyphrases
- reinforcement learning
- multi agent
- function approximation
- piecewise linear
- objective function
- reinforcement learning algorithms
- utility function
- model free
- agent architecture
- state space
- learning algorithm
- intelligent agents
- dynamic programming
- temporal difference learning
- temporal difference
- action space
- learning capabilities
- reinforcement learning methods
- multi agent reinforcement learning
- relational reinforcement learning
- robotic control
- markov decision processes
- multi attribute
- data sets
- optimal policy
- supervised learning
- control system
- learning process
- machine learning
- real world