Learning From Imperfect Demonstrations From Agents With Varying Dynamics.
Zhangjie CaoDorsa SadighPublished in: IEEE Robotics Autom. Lett. (2021)
Keyphrases
- learning agents
- minority game
- cooperative
- prior knowledge
- learning systems
- knowledge acquisition
- learned knowledge
- learning tasks
- learning algorithm
- supervised learning
- learning process
- multi agent systems
- reinforcement learning
- online learning
- decision theoretic
- active learning
- software agents
- agent architecture
- learning mechanism
- mobile devices
- agent behavior