Abstract
Evolution of cooperation and competition can appear when multiple adaptive agents share a biological, social, or technological niche. In the present work we study how cooperation and competition emerge between autonomous agents that learn by reinforcement while using only their raw visual input as the state representation. In particular, we extend the Deep Q-Learning framework to multiagent environments to investigate the interaction between two learning agents in the well-known video game Pong. By manipulating the classical rewarding scheme of Pong we show how competitive and collaborative behaviors emerge. We also describe the progression from competitive to collaborative behavior when the incentive to cooperate is increased. Finally we show how learning by playing against another adaptive agent, instead of against a hard-wired algorithm, results in more robust strategies. The present work shows that Deep Q-Networks can become a useful tool for studying decentralized learning of multiagent systems coping with high-dimensional environments.
Highlights
In the ever-changing world biological and engineered agents need to cope with unpredictability
Instead of a single agent playing against a hardcoded algorithm, we explore how multiple agents controlled by autonomous Deep Q-Network (DQN) learn to cooperate and compete while sharing a high-dimensional environment and being fed only raw visual input
In the present work we demonstrated that agents controlled by autonomous Deep Q-Networks (DQNs) are able to learn a two player video game such as Pong from raw sensory data
Summary
In the ever-changing world biological and engineered agents need to cope with unpredictability. By learning from trial-and-error an animal, or a robot, can adapt its behavior in a novel or changing environment. This is the main intuition behind reinforcement learning [1, 2]. A reinforcement learning agent modifies its behavior based on the rewards it collects while interacting with the environment. Collective animal behavior [4] and distributed control systems are important examples of multiple autonomous actors in dynamic environments. Phenomena such as cooperation, communication, and competition may emerge in reinforced multiagent systems
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
