A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learning

Dong-Ki Kim
Dong-Ki Kim
Matthew Riemer
Matthew Riemer
Chuangchuang Sun
Chuangchuang Sun
Marwa Abdulhai
Marwa Abdulhai
Sebastian Lopez-Cot
Sebastian Lopez-Cot
Cited by: 0|Bibtex|Views6
Other Links: arxiv.org

Abstract:

A fundamental challenge in multiagent reinforcement learning is to learn beneficial behaviors in a shared environment with other agents that are also simultaneously learning. In particular, each agent perceives the environment as effectively non-stationary due to the changing policies of other agents. Moreover, each agent is itself cons...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments