arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2309.04085cs.ROcs.LG
收藏

ECoDe:一种样本高效的机器人智能体协同设计方法

ECoDe: A Sample-Efficient Method for Co-Design of Robotic Agents

Deakin University(迪肯大学);Applied Artificial Intelligence Institute(应用人工智能学院)

Kishan R. Nagiredla, Buddhika L. Semage, Arun Kumar A., Thommen G. Karimpanal, Santu Rana

AI总结:

针对自主机器人智能体协同设计优化面临的样本效率低的问题,提出基于多保真度探索策略的ECoDe方法,通过通用策略学习器热启动控制器学习,在多种设计问题上表现优于基线并产生有趣的设计更改。

摘要:

协同设计自主机器人智能体需要同时优化智能体的控制器和物理设计。其固有的双层优化形式需要一个由内部控制优化驱动的外环设计优化。当设计空间较大且每次设计评估都涉及用于控制优化的数据密集型强化学习过程时,这会带来挑战。为了提高协同设计的样本效率,我们提出了一种基于多保真度的探索策略,在该策略中,我们通过通用策略学习器将设计空间中学习到的控制器联系起来,以热启动后续的控制器学习问题。在广泛的智能体设计问题上进行的实验表明,与基线相比,我们的方法具有优越性。此外,对优化设计的分析显示了有趣的设计更改,包括设计简化和非直观的更改。

英文摘要:

Co-designing autonomous robotic agents involves simultaneously optimizing the controller and physical design of the agent. Its inherent bi-level optimization formulation necessitates an outer loop design optimization driven by an inner loop control optimization. This can be challenging when the design space is large and each design evaluation involves a data-intensive reinforcement learning process for control optimization. To improve the sample efficiency of co-design, we propose a multi-fidelity-based exploration strategy in which we tie the controllers learned across the design spaces through a universal policy learner for warm-starting subsequent controller learning problems. Experiments performed on a wide range of agent design problems demonstrate the superiority of our method compared to baselines. Additionally, analysis of the optimized designs shows interesting design alterations, including design simplifications and non-intuitive alterations.

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。

↑