Several methods able to generate adversarial samples make use of gradients, which usually are not available to an attacker in real-world scenarios.
Designing optimal soft modular robots is difficult, due to non-trivial interactions between morphology and controller.
Notably, the KIEA framework is EA-agnostic (i. e., it works with any evolutionary algorithm), problem-independent (i. e., it is not dedicated to a specific type of problems), expandable (i. e., its knowledge base can grow over time).
We apply this methodology, in silico, to six test cases of urban networks made of hundreds of nodes, and find that GI produces consistent gains in delivery probability in four cases.
We present a two-level optimization scheme that combines the advantages of evolutionary algorithms with the advantages of Q-learning.
Ranked #1 on OpenAI Gym on CartPole-v1
Furthermore, we propose that this distinction is decided by the evolutionary process, thus allowing evo-RL to be adaptive to different environments.
Although very effective, evolutionary algorithms rely heavily on having a large population of individuals (i. e., network architectures) and is therefore memory expensive.
Hebbian learning is a biologically plausible mechanism for modeling the plasticity property in artificial neural networks (ANNs), based on the local interactions of neurons.
Inspired by biology, plasticity can be modeled in artificial neural networks by using Hebbian learning rules, i. e. rules that update synapses based on the neuron activations and reinforcement signals.
We perform extensive tests of different DOWSN configurations on a benchmark made up of continuous optimization problems; we analyze the influence of the network parameters (number of nodes, inter-node communication period and probability of accepting incoming solutions) on the optimization performance.
Many real-world control and classification tasks involve a large number of features.