DeepAI AI Chat
Log In Sign Up

Deep Decentralized Reinforcement Learning for Cooperative Control

by   Florian Köpf, et al.

In order to collaborate efficiently with unknown partners in cooperative control settings, adaptation of the partners based on online experience is required. The rather general and widely applicable control setting, where each cooperation partner might strive for individual goals while the control laws and objectives of the partners are unknown, entails various challenges such as the non-stationarity of the environment, the multi-agent credit assignment problem, the alter-exploration problem and the coordination problem. We propose new, modular deep decentralized Multi-Agent Reinforcement Learning mechanisms to account for these challenges. Therefore, our method uses a time-dependent prioritization of samples, incorporates a model of the system dynamics and utilizes variable, accountability-driven learning rates and simulated, artificial experiences in order to guide the learning process. The effectiveness of our method is demonstrated by means of a simulated, nonlinear cooperative control task.


page 1

page 2

page 3

page 4


MA2QL: A Minimalist Approach to Fully Decentralized Multi-Agent Reinforcement Learning

Decentralized learning has shown great promise for cooperative multi-age...

Intrinsically-Motivated Goal-Conditioned Reinforcement Learning in Multi-Agent Environments

How can a population of reinforcement learning agents autonomously learn...

Multi-agent Reinforcement Learning for Networked System Control

This paper considers multi-agent reinforcement learning (MARL) in networ...

Cooperative multi-agent reinforcement learning for high-dimensional nonequilibrium control

Experimental advances enabling high-resolution external control create n...

On Solving Cooperative MARL Problems with a Few Good Experiences

Cooperative Multi-agent Reinforcement Learning (MARL) is crucial for coo...

Multi-agent Databases via Independent Learning

Machine learning is rapidly being used in database research to improve t...