[go: up one dir, main page]

Jha et al. - Google Patents

Local Policy Optimization for Trajectory-Centric Reinforcement Learning

Jha et al.

View PDF
Document ID
1321714978515878143
Author
Jha D
Kolaric P
Raghunathan A
Lewis F
Benosman M
Romeres D
Nikovski D

External Links

Snippet

The goal of this paper is to present a method for simultaneous trajectory and local stabilizing policy optimization to generate local policies for trajectory-centric model-based reinforcement learning (MBRL). This is motivated by the fact that global policy optimization …
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
    • G05B13/0265—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
    • 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
    • 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
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00—Program-control systems
    • G05B2219/30—Nc systems
    • G05B2219/39—Robotics, robotics to robotics hand

Similar Documents

Publication Publication Date Title
EP3924884B1 (en) System and method for robust optimization for trajectory-centric model-based reinforcement learning
Choi et al. Reinforcement learning for safety-critical control under model uncertainty, using control lyapunov functions and control barrier functions
Gribovskaya et al. Learning non-linear multivariate dynamics of motion in robotic manipulators
Liu et al. Gaussian processes for learning and control: A tutorial with examples
Kamthe et al. Data-efficient reinforcement learning with probabilistic model predictive control
Levine et al. Learning neural network policies with guided policy search under unknown dynamics
Castillo et al. Intelligent adaptive model-based control of robotic dynamic systems with a hybrid fuzzy-neural approach
Rozo et al. Learning optimal controllers in human-robot cooperative transportation tasks with position and force constraints
Aydinoglu et al. Consensus complementarity control for multi-contact mpc
Izadbakhsh et al. Robust adaptive control of robot manipulators using Bernstein polynomials as universal approximator
Krug et al. Model predictive motion control based on generalized dynamical movement primitives
Russel et al. Robust constrained-MDPs: Soft-constrained robust policy optimization under model uncertainty
Sacks et al. Learning sampling distributions for model predictive control
Kolaric et al. Local policy optimization for trajectory-centric reinforcement learning
Ewerton et al. Learning trajectory distributions for assisted teleoperation and path planning
Zhang et al. Safety‐critical control for robotic systems with uncertain model via control barrier function
Gao Optimizing robotic arm control using deep Q-learning and artificial neural networks through demonstration-based methodologies: A case study of dynamic and static conditions
Umlauft et al. Bayesian uncertainty modeling for programming by demonstration
Medina et al. Considering uncertainty in optimal robot control through high-order cost statistics
Rezazadeh et al. Learning contraction policies from offline data
Ewerton et al. Reinforcement learning of trajectory distributions: Applications in assisted teleoperation and motion planning
Jha et al. Local Policy Optimization for Trajectory-Centric Reinforcement Learning
Jha et al. Robust optimization for trajectory-centric model-based reinforcement learning
Russel et al. Lyapunov robust constrained-MDPs: Soft-constrained robustly stable policy optimization under model uncertainty
Dani et al. Reinforcement learning for image-based visual servo control