Nothing Special   »   [go: up one dir, main page]

De Lellis et al., 2023 - Google Patents

CT-DQN: Control-tutored deep reinforcement learning

De Lellis et al., 2023

View PDF
Document ID
14781752081995401367
Author
De Lellis F
Coraggio M
Russo G
Musolesi M
dI Bernardo M
Publication year
Publication venue
Learning for Dynamics and Control Conference

External Links

Snippet

One of the major challenges in Deep Reinforcement Learning for control is the need for extensive training to learn the policy. Motivated by this, we present the design of the Control- Tutored Deep Q-Networks (CT-DQN) algorithm, a Deep Reinforcement Learning algorithm …
Continue reading at proceedings.mlr.press (PDF) (other versions)

Classifications

    • 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
    • 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
    • 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
    • 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

Similar Documents

Publication Publication Date Title
Wabersich et al. Linear model predictive safety certification for learning-based control
Yu et al. Mopo: Model-based offline policy optimization
Dai et al. Lyapunov-stable neural-network control
Ni et al. Adaptive learning in tracking control based on the dual critic network design
Liu et al. Meta-reward-net: Implicitly differentiable reward learning for preference-based reinforcement learning
Pan et al. Model reference composite learning control without persistency of excitation
Xu et al. Knowledge transfer in multi-task deep reinforcement learning for continuous control
CN111008449A (en) Acceleration method for deep reinforcement learning deduction decision training in battlefield simulation environment
Dumlu Design of a fractional-order adaptive integral sliding mode controller for the trajectory tracking control of robot manipulators
Joshi et al. Design and flight evaluation of deep model reference adaptive controller
Ure et al. Health aware planning under uncertainty for uav missions with heterogeneous teams
Behzadan et al. The faults in our pi stars: Security issues and open challenges in deep reinforcement learning
De Lellis et al. CT-DQN: Control-tutored deep reinforcement learning
Zhang et al. Model‐Free Attitude Control of Spacecraft Based on PID‐Guide TD3 Algorithm
Krishnakumar et al. Hybrid fuzzy logic flight controller synthesis via pilot modeling
Zheng et al. Adaptive policy learning for offline-to-online reinforcement learning
Alsalti et al. Data-driven nonlinear predictive control for feedback linearizable systems
Gu et al. A human-centered safe robot reinforcement learning framework with interactive behaviors
Liu et al. How to guide your learner: Imitation learning with active adaptive expert involvement
Long et al. Online Optimal Control of Robotic Systems with Single Critic NN‐Based Reinforcement Learning
Zhang et al. Research on adaptive non-singular fast terminal sliding mode control based on variable exponential power reaching law in manipulators
Pacelli et al. Robust control under uncertainty via bounded rationality and differential privacy
Xian et al. Control of quadrotor robot via optimized nonlinear type-2 fuzzy fractional PID with fractional filter: Theory and experiment
Liu et al. Design of an interval type-2 fuzzy neural network sliding mode robust controller for higher stability of magnetic spacecraft attitude control
De Lellis et al. Control-tutored reinforcement learning: Towards the integration of data-driven and model-based control