Reinforcement learning-driven dual neighborhood structure artificial bee colony algorithm for continuous optimization problem
0
Citation
60
Reference
10
Related Paper
Keywords:
Optimization algorithm
In order to improve control performance in various control fields, it is important to model the controlled object accurately. In this case, the quality of the model is considerably influenced by the structure of the model determined by the engineer. An element description method is a method that can optimize not only parameters but also the structure of the model. Therefore, it is possible to search over a wide range without being restricted by human design. However, this considerably increases the search space, and it is easy to fall into a local solution. In this study, the artificial bee colony algorithm is combined with the element description method to improve its search ability. The artificial bee colony algorithm is known to be effective for high-dimensional and multimodal problems. The performance of the proposed method is validated using a heat sealing system in packaging machinery. The proposed method is evaluated in comparison with the genetic algorithm, which is a conventional method. Experiments confirm that the local solution avoidance performance of the artificial bee colony algorithm is significantly better than that of the genetic algorithm.
Cite
Citations (4)
This paper presents an improved artificial bee colony algorithm. Under the framework of the basic artificial bee colony algorithm, this paper redefines the artificial bee colony and introduces search strategies for group escape and foraging based on Levy flight. The proposed algorithm is named artificial bee colony algorithm based on escaped foraging strategy (EFSABC).There are different strategies for scout bees, onlookers, and free bees searching for honey sources in the EFSABC: all working bees relinquish old honey sources due to disturbance, and select different routines to seek new honey sources. Sixteen typical high-dimensional standard functions are used to verify the effectiveness of the proposed algorithm. The EFSABC algorithm outperforms the traditional artificial bee colony algorithm in all aspects.
Bees algorithm
Cite
Citations (15)
Reinforcement Learning continues to show promise in solving problems in new ways. Recent publications have demonstrated how utilizing a reinforcement learning approach can lead to a superior policy for optimization. While previous works have demonstrated the ability to train without gradients, most recent works has focused on the simpler regression problems. This work will show how a Multi-Agent Reinforcement Learning approach can be used to optimize models in training without the need for the gradient of the loss function, and how this approach can benefit defense applications.
Presentation (obstetrics)
Cite
Citations (0)
The basic artificial bee colony algorithm gets local extremum easily and converges slowly in optimization problems of the multi-object function. In order to enhance the global search ability of basic artificial bee colony algorithm, an improved method of artificial bee colony algorithm is proposed in this paper. The basic idea of this method is as follows: On the basis of traditional artificial bee colony algorithm, the solution vectors that found by each bee colony are recombined after each iteration, then the solution vectors of combinations are evaluated again, thus the best result is found in this iteration. In this way the possibility of sticking at local extremum is reduced. Finally the simulation experiment has been finished. The simulation experiment results have shown that the method proposed in this paper is feasible and effective, it is better than basic artificial bee colony algorithm in the global search ability.
Basis (linear algebra)
Cite
Citations (8)
Reinforcement learning is the problem of autonomously learning a policy guided only by a reward function. We evaluate the performance of the Proximal Policy Optimization (PPO) reinforcement learning algorithm on a sensor management task and study the influence of several design choices about the network structure and reward function. The chosen sensor management task is optimizing the sensor path to speed up the localization of an emitter using only bearing measurements. Furthermore, we discuss generic advantages and challenges when using reinforcement learning for sensor management.
Q-learning
Cite
Citations (12)
Q-learning
Spectrum management
Cite
Citations (13)
Learning a high-performance trade execution model via reinforcement learning (RL) requires interaction with the real dynamic market. However, the massive interactions required by direct RL would result in a significant training overhead. In this paper, we propose a cost-efficient reinforcement learning (RL) approach called Deep Dyna-Double Q-learning (D3Q), which integrates deep reinforcement learning and planning to reduce the training overhead while improving the trading performance. Specifically, D3Q includes a learnable market environment model, which approximates the market impact using real market experience, to enhance policy learning via the learned environment. Meanwhile, we propose a novel state-balanced exploration scheme to solve the exploration bias caused by the non-increasing residual inventory during the trade execution to accelerate model learning. As demonstrated by our extensive experiments, the proposed D3Q framework significantly increases sample efficiency and outperforms state-of-the-art methods on average trading cost as well.
Q-learning
Cite
Citations (1)
Code (set theory)
Cite
Citations (5)
Unmanned Aerial Vehicle (UAV) is increasingly becoming an important tool used for a variety of tasks. In addition, Reinforcement Learning (RL) is a popular research topic. In this paper, these two fields are combined together and we apply the reinforcement learning into the UAV field, promote the application of reinforcement learning in our real life. We design a reinforcement learning framework named ROS-RL, this framework is based on the physical simulation platform Gazebo and it can address the problem of UAV motion in continuous action space. We can connect our algorithms into this framework through ROS and train the agent to control the drone to complete some tasks. We realize the autonomous landing task of UAV using three different reinforcement learning algorithms in this framework. The experiment results show the effectiveness of algorithm in controlling UAV which flights in a simulation environment close to the real world.
Drone
Cite
Citations (4)
Artificial Bee colony algorithm is a modern swarm intelligence algorithm. This paper proposes a modified version of artificial bee colony algorithm called “Adaptive Artificial Bee Colony” (AABC). This paper compares between standard bee colony algorithm and the proposed adaptive bee colony algorithm through traveling salesman problem. Traveling salesman problem is one of the most common problems in the searching techniques evaluation, so the paper considers it as an experimental case for the algorithms' performance discrimination. The experiments were repeated across different benchmarks. The proposed adaptive artificial bee colony algorithm presents more efficiency than standard artificial bee colony algorithm. The final solution fitness value is enhanced by around 8% in adaptive artificial bee colony algorithm comparing to standard artificial bee colony algorithm's solution.
Swarm intelligence
Cite
Citations (11)