The cultivation of autonomous strategic coordination systems

Recently, reinforcement learning has been exhibited as being capable of providing base-level reasoning towards agent-based intelligence. Agents have had applications of reinforcement learning applied from simpler problem spaces (such as learning how to play with virtual cards), to learning how to make a physical robot walk. With reinforcement learning exhibiting capabilities to provide intelligence towards an individual agent, a question becomes how well could a reinforcement learning agent be able to manage multiple individual agents that have their execution of tasks abstracted. This challenge is important to recognize when we consider more advanced applications of reinforcement learning, such as leveraging reinforcement learning to conduct strategic coordination. In our studies, we have developed a system that leveraged reinforcement learning in an abstracted competitive strategic environment (currently, a real-time strategy (RTS) engine) to evaluate the effectiveness of reinforcement learning in automating the strategic approach of individual agents. To do this, we've defined several objectives for our reinforcement learning agent to perform (eg. offense, defense, economy). Given each one of these tasks, we can incentivize and disincentivize based on both general and objective-specific metrics. Based on the cultivation of autonomous strategic coordination systems, we believe this process will enable more robust situational responses in the future for autonomous, cooperative systems, and enable automated strategic response systems in operational domains.