[go: up one dir, main page]

Boloka et al., 2021 - Google Patents

Knowledge transfer using model-based deep reinforcement learning

Boloka et al., 2021

View PDF
Document ID
1877457442355883430
Author
Boloka T
Makondo N
Rosman B
Publication year
Publication venue
2021 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA)

External Links

Snippet

Deep reinforcement learning has recently been adopted for robot behavior learning, where robot skills are acquired and adapted from data generated by the robot while interacting with its environment through a trial-and-error process. Despite this success, most model-free …
Continue reading at www.raillab.org (PDF) (other versions)

Classifications

    • 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
    • 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
    • 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
    • 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
    • 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
    • G06N5/00—Computer systems utilising knowledge based models
    • G06N5/04—Inference methods or devices
    • 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
    • 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
    • G06Q—DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management, e.g. organising, planning, scheduling or allocating time, human or machine resources; Enterprise planning; Organisational models
    • 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
    • G05B2219/39376—Hierarchical, learning, recognition and skill level and adaptation servo level

Similar Documents

Publication Publication Date Title
Boney et al. Regularizing model-based planning with energy-based models
Shahid et al. Learning continuous control actions for robotic grasping with reinforcement learning
Shaik et al. Adaptive Control Through Reinforcement Learning: Robotic Systems in Action
Yamaguchi et al. Neural networks and differential dynamic programming for reinforcement learning problems
Lim et al. Prediction of reward functions for deep reinforcement learning via Gaussian process regression
Krug et al. Model predictive motion control based on generalized dynamical movement primitives
Kicki et al. Fast kinodynamic planning on the constraint manifold with deep neural networks
Tavassoli et al. Learning skills from demonstrations: A trend from motion primitives to experience abstraction
Ota et al. Data-efficient learning for complex and real-time physical problem solving using augmented simulation
Marino et al. Modeling and planning under uncertainty using deep neural networks
Sleiman et al. Guided reinforcement learning for robust multi-contact loco-manipulation
Boloka et al. Knowledge transfer using model-based deep reinforcement learning
Xue et al. Logic-skill programming: An optimization-based approach to sequential skill planning
Bilal et al. Beyond Success: Quantifying Demonstration Quality in Learning from Demonstration
Deng et al. Hierarchical robot learning for physical collaboration between humans and robots
Tanneberg et al. Deep spiking networks for model-based planning in humanoids
Modery et al. Assisting humans in human-robot collaborative assembly contexts through deep q-learning
Caamaño et al. Introducing synaptic delays in the NEAT algorithm to improve modelling in cognitive robotics
Srinivasan et al. Path planning with user route preference-A reward surface approximation approach using orthogonal Legendre polynomials
Bondre et al. Deep reinforcement learning algorithms: A comprehensive overview
Fabisch Learning and generalizing behaviors for robots from human demonstration
Taylor et al. Integrating human demonstration and reinforcement learning: Initial results in human-agent transfer
Govindaraju et al. Enhancing Knot-Tying With Max-Margin Q-Learning: A Study on Trajectory Transfer and Lookahead Policies
Ecker Iterative linear quadratic regulator for collision-free trajectory optimization and model predictive control of a timber crane
Oikonomou et al. Online prediction of novel trajectories using a library of movement primitives