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,”
Generalizing Movements with Information-Theoretic Stochastic Optimal Control
Journal of Aerospace Information Systems ; 11 , 9 ; 579-595
2014-09-26
17 pages
Article (Journal)
Electronic Resource
English
Generalizing Interval Matrix Operations for Design
Online Contents | 1997
|Generalizing CRASH3 for reconstructing specific accidents
Automotive engineering | 1987
|Generalizing CRASH3 for Reconstructing Specific Accidents
SAE Technical Papers | 1987
|Generalizing the Bicircular Restricted Four-Body Problem
AIAA | 2020
|