Swarm Intelligence最新文献

In swarm decision making, hand-crafting agents’ rules that use local information to achieve desirable swarm-level behaviours is a non-trivial design problem. Instead of relying entirely on swarm experts for designing these local rules, machine learning (ML) algorithms can be utilised for learning some of the local rules by mapping an agent’s perception to an appropriate action. To facilitate this process, we propose the use of Machine Education (ME) as a systematic approach for designing a curriculum for teaching the agents the required skills to autonomously select appropriate behaviours. We study the use of ME in the context of decision-making in best-of-n problems. The proposed approach draws on swarm robotics expertise for identifying agents’ capabilities and limitations, the skills required for generating the desirable behaviours, and the corresponding performance measures. In addition, ME utilises ML expertise for the selection and development of the ML algorithms suitable for each skill. The results of the experimental evaluations demonstrate the superior efficacy of the ME-based approach over the state-of-the-art approaches with respect to speed and accuracy. In addition, our approach shows considerable robustness to changes in swarm size and to changes in sensing and communication noise. Our findings promote the use of ME for teaching swarm members the required skills for achieving complex swarm tasks.

Foraging in a swarm of robots has been investigated by many researchers, where the prevalent techniques have been hand-designed algorithms with parameters often tuned via machine learning. Our departure point is one such algorithm, where we replace a hand-coded decision procedure with reinforcement learning (RL), resulting in significantly superior performance. We situate our approach within the reinforcement learning as a rehearsal (RLaR) framework, that we have recently introduced. We instantiate RLaR for the foraging problem and experimentally show that a key component of RLaR—a conditional probability distribution function—can be modeled as a uni-modal distribution (with a lower memory footprint) despite evidence that it is multi-modal. Our experiments also show that the learned behavior has some degree of scalability in terms of variations in the swarm size or the environment.

Decentralised autonomous systems rely on distributed learning to make decisions and to collaborate in pursuit of a shared objective. For example, in swarm robotics the best-of-n problem is a well-known collective decision-making problem in which agents attempt to learn the best option out of n possible alternatives based on local feedback from the environment. This typically involves gathering information about all n alternatives while then systematically discarding information about all but the best option. However, for applications such as search and rescue in which learning the ranking of options is useful or crucial, best-of-n decision-making can be wasteful and costly. Instead, we investigate a more general distributed learning process in which agents learn a preference ordering over all of the n options. More specifically, we introduce a distributed rank learning algorithm based on three-valued logic. We then use agent-based simulation experiments to demonstrate the effectiveness of this model. In this context, we show that a population of agents are able to learn a total ordering over the n options and furthermore the learning process is robust to evidential noise. To demonstrate the practicality of our model, we restrict the communication bandwidth between the agents and show that this model is also robust to limited communications whilst outperforming a comparable probabilistic model under the same communication conditions.