“…Through the experiments, the suitability of the PhERS framework is also validated. Compared to our previous work [34] that first validated the PhERS framework, the experiments conducted in this study include more complex environments, use of a more advanced DRL-based controllers and an additional metric for more elaborate analysis so that the benefits of the proposed framework and the improved version of DRL-based controller could be further investigated.…”
Section: Methodsmentioning
confidence: 99%
“…Likewise, the communication network sends pheromone information from the agents to the main PhERS controller so that the released pheromone data is applied to the Phero-grids. A basic version of PhERS was tested for a simple environment scenario in [34].…”
“…Through the experiments, the suitability of the PhERS framework is also validated. Compared to our previous work [34] that first validated the PhERS framework, the experiments conducted in this study include more complex environments, use of a more advanced DRL-based controllers and an additional metric for more elaborate analysis so that the benefits of the proposed framework and the improved version of DRL-based controller could be further investigated.…”
Section: Methodsmentioning
confidence: 99%
“…Likewise, the communication network sends pheromone information from the agents to the main PhERS controller so that the released pheromone data is applied to the Phero-grids. A basic version of PhERS was tested for a simple environment scenario in [34].…”
Deep reinforcement learning has produced many success stories in recent years. Some example fields in which these successes have taken place include mathematics, games, health care, and robotics. In this paper, we are especially interested in multi-agent deep reinforcement learning, where multiple agents present in the environment not only learn from their own experiences but also from each other and its applications in multi-robot systems. In many real-world scenarios, one robot might not be enough to complete the given task on its own, and, therefore, we might need to deploy multiple robots who work together towards a common global objective of finishing the task. Although multi-agent deep reinforcement learning and its applications in multi-robot systems are of tremendous significance from theoretical and applied standpoints, the latest survey in this domain dates to 2004 albeit for traditional learning applications as deep reinforcement learning was not invented. We classify the reviewed papers in our survey primarily based on their multi-robot applications. Our survey also discusses a few challenges that the current research in this domain faces and provides a potential list of future applications involving multi-robot systems that can benefit from advances in multi-agent deep reinforcement learning.
“…Although the feasibility and benefits of RL have been demonstrated and expected to produce more promising results as it develops, there is a critical issue in implementing RL for swarm robotic systems in real-world applications. In the simulated environments, all data collected from individuals are used for training in a central server [16]- [18]. This dependence in a central server is also shown with Multi-Agent Reinforcement Learning (MARL) methods, which is a sub-domain of RL dealing with multi-agent problem.…”
The recent advancement of Deep Reinforcement Learning (DRL) contributed to robotics by allowing automatic controller design. Automatic controller design is a crucial approach for designing swarm robotic systems, which require more complex controller than a single robot system to lead a desired collective behaviour. Although DRL-based controller design method showed its effectiveness, the reliance on the central training server is a critical problem in the real-world environments where the robot-server communication is unstable or limited. We propose a novel Federated Learning (FL) based DRL training strategy for use in swarm robotic applications. As FL reduces the number of robot-server communication by only sharing neural network model weights, not local data samples, the proposed strategy reduces the reliance on the central server during controller training with DRL. The experimental results from the collective learning scenario showed that the proposed FL-based strategy dramatically reduced the number of communication by minimum 1600 times and even increased the success rate of navigation with the trained controller by 2.8 times compared to the baseline strategies that share a central server. The results suggest that our proposed strategy can efficiently train swarm robotic systems in the real-world environments with the limited robot-server communication, e.g. agri-robotics, underwater and damaged nuclear facilities.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.