The intertwined processes of learning and evolution in complex environmental niches have resulted in a remarkable diversity of morphological forms. Moreover, many aspects of animal intelligence are deeply embodied in these evolved morphologies. However, the principles governing relations between environmental ...
简单引述一个21年10月斯坦福的李飞飞团队发表在Nature Communications的Embodied Intelligence论文“Embodied intelligence via learning and evolution”。 摘要:在复杂的环境生态中,学习和进化的交织过程带来形态形式上的多样性。此外,动物智能的许多方面都深深地具身在这些进化的形态中。然而,对环境复杂性、进化形态和智能控...
文章要点:这篇文章主要想说,设计了一个进化强化的框架Deep Evolutionary Reinforcement Learning (DERL)来模拟人类进化的方式,然后得出结论:复杂的环境会产生能力更强的morphology(形态学,这个词有点玄学了,其实就是可以产生不同结构的智能体就完事了);进化会选择更好的morphology来继续进化,进化过程中产生了鲍德温效应(...
ARTICLE https://doi.org/10.1038/s41467-021-25874-z OPEN Embodied intelligence via learning and evolution Agrim Gupta 1✉, Silvio Savarese1, Surya Ganguli2,3,4 & Li Fei-Fei 1,4✉ The intertwined processes of learning and evolution in complex environmental niches have resulted in a ...
具身智能通过在物理世界和数字世界的学习和进化,达到理解世界、互动交互并完成任务的目标。 具身智能是由“本体”和“智能体”耦合而成且能够在复杂环境中执行任务的智能系统。 以上概念是等价的: Embodied AI = Embodied Intelligence = 具象AI = 具身智能` ...
Reinforcement learning (RL) has been widely adopted for intelligent decision-making in embodied agents due to its effective trial-and-error learning capabilities. However, most RL methods overlook the causal relationships among states and actions during policy exploration and lack the human-like ability...
Embodied intelligence is the computational approach to the design and understanding of intelligent behavior in embodied and situated agents through the consideration of the strict coupling between the agent and its environment (situatedness), mediated by
Xinrun WangCollege of Computing and Data Science, Nanyang Technological University, SingaporeBo AnCollege of Computing and Data Science, Nanyang Technological University, SingaporeWorld Scientific Publishing CompanyInternational Journal of Artificial Intelligence and Robotics Research...
the AAAI/ACM SIGAI Doctoral Dissertation Award, the MIT George M. Sprowls PhD Thesis Award in Artificial Intelligence and Decision-Making, the 2020 Samsung AI Researcher of the Year, the IROS Best Paper Award on Cognitive Robotics,...
Embodied Intelligence via Learning and Evolution Nature Comm. 2021 Rigid-bodied Robot Code&Page Evolution Gym: A Large-Scale Benchmark for Evolving Soft Robots NIPS 2021 Modular Soft Robot Code&Page Evolving Physical Instinct for Morphology and Control Co-Adaption IROS 2023 Legged Robot Code GA-base...