arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2203.03967cs.ROcs.NE
收藏

形态进化机器人终身学习方法的比较

Comparing lifetime learning methods for morphologically evolving robots

Vrije Universiteit Amsterdam(阿姆斯特丹自由大学)

Fuda van Diggelen, Eliseo Ferrante, A. E. Eiben

摘要:

机器人形态和控制器的进化同时导致了一个问题:即使父母的身体和大脑匹配良好,随机重组也可能打破这种匹配,并导致后代的身体与大脑不匹配。我们认为,这可以通过让新生机器人在出生后快速优化其遗传大脑的学习过程来缓解。我们比较了三种不同的算法来做到这一点。为此,我们考虑三个算法属性,效率,功效,以及对运行学习过程的机器人的形态差异的敏感性。

英文摘要:

Evolving morphologies and controllers of robots simultaneously leads to a problem: Even if the parents have well-matching bodies and brains, the stochastic recombination can break this match and cause a body-brain mismatch in their offspring. We argue that this can be mitigated by having newborn robots perform a learning process that optimizes their inherited brain quickly after birth. We compare three different algorithms for doing this. To this end, we consider three algorithmic properties, efficiency, efficacy, and the sensitivity to differences in the morphologies of the robots that run the learning process.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑