Reinforcement Learning with Sequences of Motion Primitives for Robust Manipulation - ENSTA Paris - École nationale supérieure de techniques avancées Paris Accéder directement au contenu
Article Dans Une Revue IEEE Transactions on Robotics Année : 2012

Reinforcement Learning with Sequences of Motion Primitives for Robust Manipulation

Résumé

Physical contact events often allow a natural decomposition of manipulation tasks into action phases and subgoals. Within the motion primitive paradigm, each action phase corresponds to a motion primitive, and the subgoals correspond to the goal parameters of these primitives. Current state-of-the-art reinforcement learning algorithms are able to efficiently and robustly optimize the parameters of motion primitives in very high-dimensional problems. These algorithms often consider only shape parameters, which determine the trajectory between the start- and end-point of the movement. In manipulation, however, it is also crucial to optimize the goal parameters, which represent the subgoals between the motion primitives. We therefore extend the policy improvement with path integrals (PI$^2$) algorithm to simultaneously optimize shape and goal parameters. Applying simultaneous shape and goal learning to sequences of motion primitives leads to the novel algorithm PI$^2$-Seq. We use our methods to address a fundamental challenge in manipulation: improving the robustness of everyday pick-and-place tasks.
Fichier non déposé

Dates et versions

hal-00766177 , version 1 (17-12-2012)

Identifiants

  • HAL Id : hal-00766177 , version 1

Citer

Freek Stulp, Evangelos Theodorou, Stefan Schaal. Reinforcement Learning with Sequences of Motion Primitives for Robust Manipulation. IEEE Transactions on Robotics, 2012, 28 (6), pp.1360-1370. ⟨hal-00766177⟩
168 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More