Deep Decentralized Reinforcement Learning for Cooperative Control
This addresses coordination challenges in multi-agent systems for applications like robotics or autonomous systems, but appears incremental in method development.
The paper tackles the problem of enabling efficient collaboration with unknown partners in cooperative control settings by proposing new modular deep decentralized Multi-Agent Reinforcement Learning mechanisms, demonstrating effectiveness on a simulated nonlinear cooperative control task.
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.