.png){kind=icon}
返回
Markovian policy network for efficient robot learning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2022.09.059.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
What poses a challenge for robot learning is the fact that considerable training samples and time are required to find an optimal policy in the high-dimensional robot state space. To mitigate this problem of robot learning, there is an incentive in incorporating appropriate prior knowledge. In this paper, a novel framework named Markovian Policy Network (MPN) is presented to take full advantage of the structural prior knowledge for robots to achieve efficient robot learning. Specifically, we first make efforts to reveal the Markov Property of the robot, which characterizes the intrinsic prior knowledge for robotic physical structure. Next, the proposed framework is constructed by employing a modified graph neural network to incorporate the Markov Property of the robot into policy networks. By exploiting the structural prior knowledge of robots in our framework, the high-dimensional original state space could be decom-posed into several low-dimensional state spaces with conditional independence to realize substantial reductions in the dimensionality of state space. Empirical results on diverse robotic systems including the challenging dexterous manipulation task, demonstrate not only the effectiveness but the robustness of the proposed MPN for robotic skill learning, delivering advancement substantially over traditional pol-icy learning methods.(c) 2022 Elsevier B.V. All rights reserved.
Keyword:
Efficient robot learning
Structural prior knowledge
Reinforcement learning
Graph neural network
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
Identification and optimal control of nonlinear systems using recurrent neural networks and reinforcement learning: An overview.png)
NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏Challenges of real-world reinforcement learning: definitions, benchmarks and analysis现实世界强化学习的挑战: 定义、基准和分析MACHINE LEARNING
OAAI
MACHINE LEARNINGIF2.9
OAAI分享收藏Fabrication of porous hollow γ-Al2O3 nanofibers by facile electrospinning and its application for water remediation静电纺丝法制备多孔中空 γ-Al2O3纳米纤维及其在水体修复中的应用
PREAI
分享收藏分享收藏Sequential learning unification controller from human demonstrations for robotic compliant manipulationNEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏
查看更多内容