Stochastic optimal control is typically used to plan a movement for a specific situation. Although most stochastic optimal control methods fail to generalize this movement plan to a new situation without replanning, a stochastic optimal control method is presented that allows reuse of the obtained policy in a new situation, as the policy is more robust to slight deviations from the initial movement plan. To improve the robustness of the policy, we employ information-theoretic policy updates that explicitly operate on trajectory distributions instead of single trajectories. To ensure a stable and smooth policy update, the ”distance” is limited between the trajectory distributions of the old and the new control policies. The introduced bound offers a closed-form solution for the resulting policy and extends results from recent developments in stochastic optimal control. In contrast to many standard stochastic optimal control algorithms, the current approach can directly infer the system dynamics from data points, and hence can also be used for model-based reinforcement learning. This paper represents an extension of the paper by Lioutikov et al. (“Sample-Based Information-Theoretic Stochastic Optimal Control,” Proceedings of 2014 IEEE International Conference on Robotics and Automation (ICRA), IEEE, Piscataway, NJ, 2014, pp. 3896–3902). In addition to revisiting the content, an extensive theoretical comparison is presented of the approach with related work, additional aspects of the implementation are discussed, and further evaluations are introduced.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Generalizing Movements with Information-Theoretic Stochastic Optimal Control


    Contributors:

    Published in:

    Publication date :

    2014-09-26


    Size :

    17 pages




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English





    Generalizing CRASH3 for reconstructing specific accidents

    Struble,D.E. / Collision Safety Engineering,US | Automotive engineering | 1987


    Generalizing CRASH3 for Reconstructing Specific Accidents

    Struble, Donald E. | SAE Technical Papers | 1987


    Optimal Coordination and Control of Posture and Movements

    Johansson, Rolf / Fransson, Per-Anders / Magnusson, Måns | BASE | 2009

    Free access

    Generalizing the Bicircular Restricted Four-Body Problem

    Negri, Rodolfo B. / Prado, Antônio F. B. A. | AIAA | 2020