Reinforcement learning using swarm intelligence-trained neural networks
Reinforcement learning using swarm intelligence-trained neural networks
复制标题
DOI：
10.1080/09528130903065497
复制
发表时间：
2010-09
影响因子：
2.2
通讯作者：
Matthew Conforth;Y. Meng
中科院分区：
文献类型：
--
作者：
Matthew Conforth;Y. Meng
本文提出了一种新的强化学习方法，该方法利用群体智能训练的神经网络(Swinn)来高效地生成各种实际问题的解。群智能算法粒子群优化(PSO)与Swinn中的训练资源分配器(TRA)相结合，用于解决特定问题。TRA作为一种启发式全局搜索方法，控制训练资源分配给不同的人工神经网络(ANN)候选拓扑，以加快系统的收敛速度；而PSO作为局部搜索算法，用于调整ANN的连接权。为了评估Swinn算法的性能，对两个强化学习案例进行了研究：双极点平衡(又名。(二级倒立摆)问题和移动机器人定位问题。大量的模拟结果成功地证明了Swinn提供了与现代神经进化技术竞争的性能，并且对于现实世界的问题是可行的。
This article proposes a new reinforcement learning method using the swarm intelligence-trained neural network (SWINN) to generate solutions to various real-world problems efficiently. The swarm intelligence algorithm, particle swarm optimisation (PSO), is combined with a training resource allocator (TRA) in SWINN for specific problems. TRA, as a heuristic global search method, controls the allocation of training resources to different candidate topologies of artificial neural networks (ANNs) to expedite the system convergence, while PSO is applied as a local search algorithm to adjust the ANNs connection weights. To evaluate the performance of the SWINN algorithm, two reinforcement learning case studies: the double pole balance (a.k.a. double inverted pendulum) problem and a mobile robot localisation problem are conducted. Extensive simulation results successfully demonstrate that SWINN offers performance that is competitive with modern neuroevolutionary techniques, and is viable for real-world problems.