Benefits of lamarckian evolution for morphologically evolving robots
暂无分享,去创建一个
Implementing lifetime learning by means of on-line evolution, we establish an indirect encoding scheme that combines Compositional Pattern Producing Networks (CPPNs) and Central Pattern Generators (CPGs) as a relevant learner and controller for open-loop gait controllers in modular robots which have evolving morphologies. Experimental validation on the morphologically evolved robots shows that a Lamarckian setup with CPPN-CPG provides substantial benefits compared to controllers learned from scratch.
[1] A. E. Eiben,et al. Improving RL power for on-line evolution of gaits in modular robots , 2016, 2016 IEEE Symposium Series on Computational Intelligence (SSCI).
[2] Hod Lipson,et al. On the Difficulty of Co-Optimizing Morphology and Control in Evolved Virtual Creatures , 2016, ALIFE.
[3] Kenneth O. Stanley,et al. A Hypercube-Based Encoding for Evolving Large-Scale Neural Networks , 2009, Artificial Life.