Federated reinforcement learning for robot motion planning with zero-shot generalization

DOI10.1016/J.AUTOMATICA.2024.111709zbMATH Open1544.93577MaRDI QIDQ6574451FDOQ6574451

Authors: Zhenyuan Yuan, Siyuan Xu, Minghui Zhu 

Publication date: 18 July 2024

Published in: Automatica (Search for Journal in Brave)

Recommendations

• Hybrid DDPG Approach for Vehicle Motion Planning
• Decentralized reinforcement learning of robot behaviors
• Safety reinforcement learning control via transfer learning
• Adaptive reinforcement learning-enhanced motion/force control strategy for multirobot systems
• Recent advances of reinforcement learning in multi-robot systems: a survey

zbMATH Keywords

motion planningreinforcement learninggeneralization

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Automated systems (robots, etc.) in control theory (93C85)

Cites Work

• Measure theory. Vol. I and II
• Concentration inequalities. A nonasymptotic theory of independence
• Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming
• Robust Control of Markov Decision Processes with Uncertain Transition Matrices
• Reinforcement learning. An introduction
• Planning Algorithms
• Natural evolution strategies
• A comprehensive survey on safe reinforcement learning
• End-to-end training of deep visuomotor policies
• Convergence rates for the stochastic gradient descent method for non-convex objective functions
• A Course in Mathematical Statistics and Large Sample Theory
• Robust Motion Planning for Uncertain Systems With Disturbances Using the Invariant-Set Motion Planner
• A Survey of Zero-shot Generalisation in Deep Reinforcement Learning

This page was built for publication: Federated reinforcement learning for robot motion planning with zero-shot generalization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6574451)