Embodied Evolutionary Learning

Learning-based heuristics for solving combinatorial optimization problems has recently attracted much academic attention. While most of the existing works only consider the single objective problem with simple constraints, many real-world problems have the multiobjective perspective and contain a rich set of constraints. This paper proposes a multiobjective deep reinforcement learning with evolutionary learning algorithm for a typical complex problem called the multiobjective vehicle routing problem with time windows (MO-VRPTW). In the proposed algorithm, the decomposition strategy is applied to generate subproblems for a set of attention models. The comprehensive context information is introduced to further enhance the attention models. The evolutionary learning is also employed to fine-tune the parameters of the models. The experimental results on MO-VRPTW instances demonstrate the superiority of the proposed algorithm over other learning-based and iterative-based approaches.

The paper presents an agent-based, computational model to simulate and analyze the collective outcome of public goods provisioning under asymmetric information. Agents that embrace different information types are conceptualized and configured to interact in an N-player public goods game where each agent group adapts to the dynamic environment using co- evolutionary learning. The impact of information type, number of players, rate of interaction, group size, and the scheme of game play are studied under different settings. The simulated results reveal interesting dynamics of strategy profiles, level of public goods provisioned, and the evolution of cooperation. Analysis of these simulated attributes provides a more holistic understanding of collective action and insights into how the effects of social dilemma can be mitigated.

This paper presents the application of evolutionary learning techniques for improving performance of robot navigation. The goal is to build an intelligent control algorithm that drives the robot in an unknown environment at the maximum allowable speed, while avoiding obstacles and keeping its rate of turns to a minimum. The robot controller is based on an artificial neural network that takes inputs from range sensors and produces outputs to control the drive motors. The ANN is evolved using a simple genetic algorithm. Two different evolutionary learning approaches are evaluated. In the first approach synaptic weights of the network are evolved, while in the second one the adaptation rules of the synapses are evolved. At the end of the evolutionary processes, both solutions resulted in best performing controllers, that can avoid collisions while maximizing linear speed and minimizing turning.

by Dana H. Ballard, MIT Press, 1997. $45.00 (xxii+307 pages) ISBN 0 262 02420 9.

Multi-copter is required to move ascending flight, descending flight and hovering flight with adequate controlled behavior in the air environment. This study aims at acquiring autonomous behavior for such a multi-copter by physically modeled simulation. This multi-copter is modeled by use of the physical engine (PhysX) in a virtual environment. We use neuro-evolution to have the multi-copter acquire autonomous behavior. Namely the multi- copter behavior is controlled by an artificial neural network (ANN), The ANN is evolved to let it learn proper behavior by evolutionary computation (GA). Simulation results verify that the multi-copter can acquire autonomous behaviors.

With the development of Internet of Medical Things(IOMT), a lot of medical data are stored and released for both scientific research and practical applications. Accurate medical data is very valuable, but it also brings a huge risk of privacy leakage. Moreover, improving the privacy of data often leads to the reduction of data validity. Privacy and effectiveness are in conflict, and their balance is a typical multi-objective optimization problem (MOP). In this paper, we try to use differential privacy to disturb medical data to protect personal privacy. We propose the Environment Switching Algorithm (ESA) based on evolutionary learning to solve this MOP. ESA has excellent performance, which can ensure convergence speed and optimization performance at the same time. The result of optimization is a pareto front (PF) of huge scale, which includes solutions with different characteristics. We put forward a method of double clustering to select the appropriate solution from PF. Based on the above, we conclude the whole method as Flexible Differential Privacy Algorithm based on Evolutionary Learning (FDPEL). FDPEL can realize flexible differential privacy for medical data, while ensuring data privacy and data validity. FDPEL is suitable for privacy protection of medical data of different scales, which makes it have a practical applications value.

L’enquête TétrAfigap relancée

Nowadays, data in power system have become big data and have attracted much attention due to the huge treasure buried in them. There is a great demand for forecasting electrical load and avoiding unexpected losses in power system. How to deal with the tremendous amount of data and capture the hidden information has become an important question. Deep learning can effectively extract the intrinsic features from data, achieving state-of-the-art performance in electrical load forecasting. However, it is often stuck in local minimum because of random initialization of parameters and structure selection in the stochastic gradient descent (SGD) so that its robust performance which is attached importance to in electrical practice is not guaranteed. To address that problem, in this paper, we proposed a robust method for accurate electrical load forecasting on the basis of the evolutionary algorithm which can avoid local minimum trap in deep learning trained by SGD. Specially, the deep learning model's structure and parameters will be optimized by not only gradient but also survival of the fittest through selection, crossover, mutation, and replacement on different models. Experimental results on the real electrical load data demonstrate the effectiveness of the evolutionary deep learning model in terms of accuracy of electrical load forecasting.

We present a complete design of agents for the RoboCup Rescue Simulation problem that uses an evolutionary reinforcement learning mechanism called XCS, a version of Holland’s Genetic Classifiers Systems, to decide the number of ambulances required to rescue a buried civilian. We also analyze the problems implied by the rescue simulation and present solutions for every identified sub-problem using multi-agent cooperation and coordination built over a subsumption architecture. Our agents’ classifier systems were trained in different disaster situations. Trained agents outperformed untrained agents and most participants of the 2004 RoboCup Rescue Simulation League competition. This system managed to extract general rules that could be applied on new disaster situations, with a computational cost of a reactive rule system.KeywordsAlive AgentDisaster SituationEvolutionary ReinforcementSystem Genetic ProgramAgent TeamThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

This paper considers an evolutionary extreme learning machine (ELM) based on chemical reaction optimization (CRO) to overcome the drawbacks of ELM, such as the unavoidable existence of a set of unnecessary or non-optimal hidden biases and input weights. By using CRO algorithm to determine the hidden biases and input weights according to both the norm of output weights and the root mean squared error, the classification performance of optimized ELM can be improved. The experimental results on some real benchmark problems show that the proposed method can achieve higher classification accuracy than both other compared evolutionary ELMs and original ELM.

Automata with hierarchical control and evolutionary learning

Recent deep neural networks based techniques, especially those equipped with the ability of self-adaptation in the system level such as deep reinforcement learning (DRL), are shown to possess many advantages of optimizing robot learning systems (e.g., autonomous navigation and continuous robot arm control.) However, the learning-based systems and the associated models may be threatened by the risks of intentionally adaptive (e.g., noisy sensor confusion) and adversarial perturbations from real-world scenarios. In this paper, we introduce timing-based adversarial strategies against a DRL-based navigation system by jamming in physical noise patterns on the selected time frames. To study the vulnerability of learning-based navigation systems, we propose two adversarial agent models: one refers to online learning; another one is based on evolutionary learning. Besides, three open-source robot learning and navigation control environments are employed to study the vulnerability under adversarial timing attacks. Our experimental results show that the adversarial timing attacks can lead to a significant performance drop, and also suggest the necessity of enhancing the robustness of robot learning systems.

Evolutionary Learning and Optimization Using Genetic Programming Paradigm

The claim is advanced for recognizing evolutionary learning as the generative principle of world politics. Immanuel Kant was the first to specify a “natural” process leading toward “perpetual peace.” The long cycle, seen as the process of structural change. is explained with the help of a Parsonian learning model and a social evolutionary model and is argued to be coupled with the Kantian process. The long cycle defines the agenda for change in the major institutional complexes of world politics and deepens our understanding of the conditions for the control of global war.

E-Net: Evolutionary neural network synthesis