Fundamental Research on Advanced Evolutionary and Adaptive Systems

a.r eresearch Results on volutionary Computation我们proposed a robust real-coded GA using thecombination of two crossovers，UNDX-m and EDX. It can deal both ridge-structure function whose dimension reaches more than hundreds我们提倡一个新的evolutionary algorithm called ANS （Adaptive neighboring）Search with a crossover-like mutation to optimize high dimensional deceptive multimodal我们发现一个hypothesis call "UV-phenomenon" which explains failures of global search byGA. It suggests UV-structures as hard landscape structures that will cause theUV-phenomenon.B.Research Results on Reinforcement Learning我们提倡一个新的crossover LUNDX-m whichuses only in-dimensional latent variables. LUNDX-m可以treat with high-dimensional ill-scaledstructures called k -tablet structure. In multi-agent reinforcement learning systems，这是重要的，如何分享一个reward among all agents.我们被认为是必要的和需要的condition to preserve the rationality to realize cooperative behaviors.我们提倡一个政策function presentation that consists of a stochastic binary decision tree. We applied it to anactor-critic algorithm for the problems that have enormous similar actions.我们投资areinforcement learning of walking behavior for a four-legged robot. We presented. a new actor-criticalgorithm,其中actor selects a continuous action from its bounded action space by using the normal我们提供了一种基于新simulation-based distributed reinforcement learning approach解决方案大计划方案under uncertain environment. We applied it to real sewerage controlsystems。

A.Research Results on Evolutionary Computation・We proposed a robust real-coded GA using the combination of two crossovers, UNDX-m and EDX. It can deal both ridge-structure function whose dimension reaches more than hundreds and multi-peak functions.・We proposed a new evolutionary algorithm called ANS (Adaptive neighboring Search) with a crossover-like mutation to optimize high dimensional deceptive multimodal functions.・We found a hypothesis call "UV-phenomenon" which explains failures of global search by GA. It suggests UV-structures as hard landscape structures that will cause the UV-phenomenon.B.Research Results on Reinforcement Learning・We proposed a new crossover LUNDX-m which uses only in-dimensional latent variables. LUNDX-m can treat with high-dimensional ill-scaled structures called k -tablet structure.・In multi-agent reinforcement learning systems, it is important how to share a reward among all agents. We derived the necessary and sufficient condition to preserve the rationality to realize cooperative behaviors.・We proposed a policy function representation that consists of a stochastic binary decision tree. We applied it to an actor-critic algorithm for the problems that have enormous similar actions.・We investigated a reinforcement learning of walking behavior for a four-legged robot. We presented. a new actor-critic algorithm, in which the actor selects a continuous action from its bounded action space by using the normal distribution.・We proposed a new simulation-based distributed reinforcement learning approach that solves large planning problems under uncertain environment. We applied it to real sewerage control systems.