[go: up one dir, main page]

Jha et al., 2019 - Google Patents

Robust optimization for trajectory-centric model-based reinforcement learning

Jha et al., 2019

View PDF
Document ID
16791750663601743939
Author
Jha D
Kolaric P
Romeres D
Raghunathan A
Benosman M
Nikovski D
Publication year
Publication venue
Workshop on Safety and Robustness in Decision Making at NeurIPS

External Links

Snippet

This paper presents a method to perform robust trajectory optimization for trajectory-centric Model-based Reinforcement Learning (MBRL). We propose a method that allows us to use the uncertainty estimates present in predictions obtained from a model-learning algorithm to …
Continue reading at shadow.merl.com (PDF) (other versions)

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
    • G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
    • G05B13/048—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators using a predictor
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/0265—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion
    • G05B13/027—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion using neural networks only
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/0205—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric not using a model or a simulator of the controlled system
    • G05B13/021—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric not using a model or a simulator of the controlled system in which a variable is automatically adjusted to optimise the performance
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N99/00—Subject matter not provided for in other groups of this subclass
    • G06N99/005—Learning machines, i.e. computer in which a programme is changed according to experience gained by the machine itself during a complete run
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computer systems based on biological models
    • G06N3/02—Computer systems based on biological models using neural network models
    • G06N3/04—Architectures, e.g. interconnection topology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computer systems based on biological models
    • G06N3/02—Computer systems based on biological models using neural network models
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B17/00—Systems involving the use of models or simulators of said systems
    • G05B17/02—Systems involving the use of models or simulators of said systems electric
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computer systems utilising knowledge based models
    • G06N5/02—Knowledge representation
    • G06N5/022—Knowledge engineering, knowledge acquisition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computer systems utilising knowledge based models
    • G06N5/04—Inference methods or devices
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06F—ELECTRICAL DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/50—Computer-aided design
    • G06F17/5009—Computer-aided design using simulation

Similar Documents

Publication Publication Date Title
EP3924884B1 (en) System and method for robust optimization for trajectory-centric model-based reinforcement learning
Dutta et al. Sherlock-a tool for verification of neural network feedback systems: demo abstract
Xiang et al. Reachability analysis and safety verification for neural network control systems
Hours et al. A parametric nonconvex decomposition algorithm for real-time and distributed NMPC
Carius et al. Constrained stochastic optimal control with learned importance sampling: A path integral approach
Lee et al. Gp-ilqg: Data-driven robust optimal control for uncertain nonlinear dynamical systems
Udekwe et al. Comparing actor-critic deep reinforcement learning controllers for enhanced performance on a ball-and-plate system
Everett Neural network verification in control
Zhang et al. Safety‐critical control for robotic systems with uncertain model via control barrier function
Zhou et al. Runtime-safety-guided policy repair
Kolaric et al. Local policy optimization for trajectory-centric reinforcement learning
Aoyama et al. Receding horizon differential dynamic programming under parametric uncertainty
Hall et al. Differentially flat learning-based model predictive control using a stability, state, and input constraining safety filter
Saha et al. Neural identification for control
Tan et al. Zero-order control barrier functions for sampled-data systems with state and input dependent safety constraints
Jha et al. Robust optimization for trajectory-centric model-based reinforcement learning
Kolaric et al. Robust optimization for trajectory-centric model-based reinforcement learning
Zhang et al. Robustified time-optimal collision-free motion planning for autonomous mobile robots under disturbance conditions
Munoz et al. Online adaptive compensation for model uncertainty using extreme learning machine-based control barrier functions
Russel et al. Lyapunov robust constrained-MDPs: Soft-constrained robustly stable policy optimization under model uncertainty
Ito et al. Second-order bounds of Gaussian kernel-based functions and its application to nonlinear optimal control with stability
Kobayashi et al. Optimal control of multi-vehicle systems with temporal logic constraints
Cubuktepe et al. Shared control with human trust and workload models
Jha et al. Local Policy Optimization for Trajectory-Centric Reinforcement Learning
Wehbeh et al. Nonlinear scenario‐based model predictive control for quadrotors with bidirectional thrust