Litcius/Paper detail

Learning Locomotion for Quadruped Robots via Distributional Ensemble Actor-Critic

Sicen Li, Yiming Pang, Panju Bai, Jiawei Li, Zhaojin Liu, Shihao Hu, Liquan Wang, Gang Wang

2024IEEE Robotics and Automation Letters14 citationsDOIOpen Access PDF

Abstract

Domain randomization introduces perturbations in the simulation to make controllers less susceptible to the reality gap, which enables remarkable sim-to-real transfer on real quadruped robots. However, aleatoric uncertainty originating from perturbations could often lead to suboptimal controllers. In this work, we present a novel algorithm called Distributional Ensemble Actor-Critic (DEAC) that blends three ideas: distributional representation of a critic, lower bounds of the value distribution, and ensembling of multiple critics and actors. Distributional representation and ensembling provide reasonable uncertainty estimates, while lower bounds of the value distribution offer finer-grained error control. The simulation results show that the controller trained by DEAC outperforms the other baselines in the domain randomization setting. The trained controller is deployed on an A1-like robot, demonstrating high-speed running and the ability to traverse diverse terrains such as slippery plates, grassland, and wet dirt.

Topics & Concepts

RobotRepresentation (politics)TraverseComputer scienceController (irrigation)TerrainDomain (mathematical analysis)Control theory (sociology)RoboticsValue (mathematics)Artificial intelligenceControl (management)Mathematical optimizationMachine learningMathematicsGeographyPolitical scienceMathematical analysisPoliticsCartographyGeodesyLawAgronomyBiologyReinforcement Learning in RoboticsModel Reduction and Neural NetworksRobotic Locomotion and Control
Learning Locomotion for Quadruped Robots via Distributional Ensemble Actor-Critic | Litcius