MPC outperforms reactive budgeting in non-stationary return environments.
problem Optimizing budget allocation under non-stationary returns.
method Receding-horizon Model Predictive Control (MPC) compared to reactive policies.
result MPC consistently outperforms reactive budgeting when return dynamics are predictable.
Model learns and plans in real-time under constraints for robotic systems.
problem Challenges in applying reinforcement learning to robotic systems, especially handling continuous state and action spaces, time/resource budget, and hard constraints.
method Combines Gaussian Process regression and Receding Horizon Control. Uses sparse spectrum Gaussian Processes for incremental model updates from sensory data.
result Demonstrates benefits of online learning on autonomous racing tasks and reusability of learned dynamics.
AdaSearch improves adaptive sensing in noisy environments.
problem Adaptive source seeking in environments with variable background signals.
method Combines global trajectory planning with principled confidence intervals.
result AdaSearch outperforms uniform sampling and other methods in simulations and hardware tests.
Efficient learning-based MPC for unknown nonlinear systems with state constraints.
problem Control of discrete-time nonlinear systems with unknown dynamics and state constraints.
method Receding horizon reinforcement learning (r-LPC) using Koopman operator-based prediction model.
result Proven closed-loop recursive feasibility, robustness, and asymptotic stability under function approximation errors.
A new approach optimizes weights in DLP for better risk-adjusted performance.
problem Optimizing time-varying weights in Double Linear Policy (DLP) for better risk-adjusted performance.
method Stochastic Model Predictive Control (SMPC) framework to maximize risk-adjusted returns while enforcing constraints.
result Empirical results show improved risk-adjusted performance and drawdown control.
MOVI learns optimal vehicle dispatch policies without models, reducing unserviced requests.
problem Optimizing vehicle dispatch to minimize passenger wait times in dynamic fleets.
method Model-free approach using Deep Q-network (DQN) for decentralized learning and centralized receding-horizon control comparison.
result DQN dispatch policy reduces unserviced requests by 76% compared to no dispatch and 20% compared to RHC.
Paper uses Apprenticeship Learning to model player behavior in interactive narratives.
problem Understanding and simulating player behavior in interactive narratives.
method Receding Horizon IRL (RHIRL) to learn reward functions and policies.
result RHIRL can learn action sequences and generate behavior similar to specific players.
We examine optimal execution models that take into account both market microstructure impact and informational costs. Informational footprint is related to order flow and is represented by the trader's influence on the flow imbalance process, while microstructure influence is captured by instantaneous price impact. We …
New algorithm optimizes exploration in unknown MDPs.
problem Optimal exploration in unknown Markov decision processes.
method Trajectory-optimization-based approximate solution using Bayesian experimental design.
result Empirically superior to intrinsic-motivation-based algorithms in convergence and model fidelity.
Neural PID controllers improve control system performance and are more interpretable.
problem Lack of interpretability in neural PID controllers limits their use in control engineering.
method Extensive study using four benchmark systems with and without noise and disturbances, applying GDNN to PID controllers.
result Neural PID controllers outperform standard PID and model-based control in most tasks.
Boosting improves control of complex systems.
problem Improving performance of controllers for dynamical systems.
method Proposes a boosting framework for online control of dynamical systems.
result An efficient boosting algorithm that combines weak controllers into a more accurate one.
Paper generalizes control contraction metrics to Finsler geometry.
problem Designing nonlinear controllers for complex geometries.
method Generalization of CCMs to Finsler geometry, providing open loop and sampled data controllers.
result Simplified computation of sampled data control without real-time shortest path computation.
Derives optimal control conditions using calculus of variations.
problem Optimizing Markov control in stochastic control problems.
method Calculus of variations approach to derive necessary conditions.
result Solves the Merton portfolio optimization problem.
Framework simplifies vision-based control and goal discovery.
problem Learning proportional control from visual data.
method Introduces NewtonianVAE for proportional control and goal discovery.
result Dramatic simplification and acceleration of vision-based controllers.
The paper introduces new tests for global controllability in hybrid systems.
problem Global controllability in hybrid systems with discrete events.
method Geometric formulation of hybrid systems and analysis of jump points.
result Hybrid systems can be globally controllable even if continuous systems are not.
This work tackles force control for contact-rich manipulation tasks with rigid robots using RL.
problem Challenges in working with real robotic hardware, especially position-controlled robots.
method Combines RL with traditional force control techniques, implementing parallel position/force control and admittance control.
result Validated methods on both simulation and real robot (UR3 e-series) for force control.
Paper studies constrained control games with a novel approximation method.
problem Games with constrained control directions.
method Approximation procedure based on L1-stability estimates and almost sure convergence. result Existence of game's value and optimal strategy for the stopper.
RL applied to TCLs for power consumption control.
problem Optimizing power consumption using TCLs with RL.
method Modelica-based reinforcement learning (Q-learning) for stochastic TCLs.
result Q-learning parameters affect controller performance.
A framework integrates machine learning with robust control for safer, more reliable systems.
problem Combining machine learning with robust control for systems with stringent safety and reliability requirements.
method Integrates Gaussian Process Regression and state-of-the-art robust controller synthesis within a framework that provides rigorous guarantees.
result Demonstrated improved performance with more data while maintaining rigorous guarantees.
Paper optimizes energy-based controller for swinging up a pendulum using entropy search.
problem Finding optimal parameters for energy-based controllers is hard.
method Bayesian optimization (Entropy Search) applied to energy-based controller design.
result Optimal controller improves performance of a swinging pendulum.
Paper uses deep reinforcement learning for better control of rocket engines during start-up phases.
problem Lack of optimal control during transient phases of liquid rocket engines.
method Deep reinforcement learning approach for optimal control of a gas-generator engine's continuous start-up phase.
result Deep reinforcement learning controller achieves highest performance and minimal computational effort.
Study local control of a specific mechanism with growth vector (4,7).
problem Local control of a mechanism with a specific growth vector.
method Controllability and extremal trajectories on the nilpotent approximation.
result Solutions of the system and examples of local extremal trajectories.
Neural ODEs control graph dynamics with low energy feedback.
problem Controlling complex dynamical systems on graphs.
method Neural Ordinary Differential Equation Control (NODEC) framework.
result NODEC learns low-energy control signals for graph dynamical systems.
Just as an explicit parameterisation of system dynamics by state, i.e., a choice of coordinates, can impede the identification of general structure, so it is too with an explicit parameterisation of system dynamics by control. However, such explicit and fixed parameterisation by control is commonplace in control theory…
Unified control theory and machine learning for safety in uncertain systems.
problem Safety guarantees for systems with measurement model uncertainty.
method Measurement-Robust Control Barrier Functions (MR-CBFs) for control synthesis.
result MR-CBFs ensure safety in perception systems with measurement model uncertainty.
Paper studies optimal control for a specific geometric problem.
problem Optimal control problem associated with the Paneitz obstacle problem.
method Existence and regularity results for optimal controls.
result Existence of optimal controls and their properties.
New method uses neural nets to control systems safely with disturbances.
problem Designing safe control laws for systems with disturbances.
method Imitation learning to train neural network controllers that satisfy CBF constraints.
result Demonstrated on a unicycle model with external disturbances.
Optimizes dividend policies in a Brownian model with controlled rates.
problem Realistic optimal dividend policies in a stochastic control problem.
method Delayed linear control strategies for refracted diffusion processes.
result Optimality of delayed linear control strategies for dividend payments.
Paper proposes a new method to optimize robot body structure and control policy.
problem Optimizing robot body structure and control policy in a coupled manner.
method Revisits co-design problem as a Stackelberg game, incorporating control adaptation dynamics.
result Stackelberg PPO outperforms standard PPO in stability and performance.
Neural network HDP improves virtual inertia control for non-inductive grids.
problem Traditional virtual inertia controllers are not suitable for non-inductive grids.
method Adaptive neural network heuristic dynamic programming (HDP) for optimal control.
result The proposed HDP controller outperforms traditional controllers in virtual inertia control.
Non-bilinear observations make optimal control harder, showing non-convex costs and non-affine optimal controllers.
problem Optimal control from bilinear observations in linear systems is challenging.
method Analytical and numerical methods to study the non-convex cost-to-go and non-affine optimal controllers.
result The Separation Principle does not hold for bilinear observations, leading to non-convex costs and non-affine optimal controllers.
Defense strategy improves controller robustness against adversarial attacks.
problem Adversarial attacks on learning-enabled controllers in CPS.
method Two-stage defense strategy treating controller and environment as black-boxes with unknown dynamics.
result Defense strategy effectively improves controller robustness in realistic control domains.
This paper considers control systems defined on Lie algebroids. After deriving basic controllability tests for general control systems, we specialize our discussion to the class of mechanical control systems on Lie algebroids. This class of systems includes mechanical systems subject to holonomic and nonholonomic const…
Survey of theoretical foundations for policy optimization in control.
problem Understanding the theoretical properties of gradient-based methods in control and reinforcement learning.
method Interdisciplinary review of optimization landscape, convergence, and sample complexity for various control problems.
result Recent theoretical results on stability and robustness in learning-based control.
Neuro-inspired RL solves complex control problems with fewer controllers.
problem Solving nonlinear control problems with unknown dynamics efficiently.
method Hierarchical RL framework combining limb coordination and reinforcement learning.
result Local LQR controllers combined with a reinforcement learner solve global nonlinear problems.
Survey combines FL and control for better adaptability and privacy.
problem Combining FL and control for better adaptability and privacy.
method Combining Federated Learning (FL) and control methods.
result Combining FL and control enhances adaptability, scalability, generalization, and privacy.
New method for handling multi-dimensional singular controls with jump costs in mean-field problems.
problem Handling jump costs in multi-dimensional singular controls.
method Introducing two-layer parametrisations to interpolate jumps on both distributional and pathwise levels.
result Derivation of a DPP and characterisation of the value function as a minimal super-solution to a quasi-variational inequality.
Researchers use Meyer-σ-fields to model information flow in irreversible investment problems.
problem Modeling information flows in stochastic control problems with jumps.
method Using Meyer-σ-fields as a tool to model information flow.
result Different signals on exogenous jumps lead to different optimal controls.
Researchers develop a method to control nonlinear systems with Koopman operator regression.
problem Controlling nonlinear systems with finite action spaces.
method Koopman operator regression for dynamics estimation and model predictive control for control.
result The method yields a linear switching predictive model for control.
A new Q-learning controller improves line follower robot control.
problem Challenges in controlling line follower robots due to unknown mechanical characteristics and uncertainties.
method Simulated annealing based Q learning method to address controller performance issues.
result The proposed controller outperforms conventional P controllers in line follower robots.
Anticipatory model generates music with control over events.
problem Controlling symbolic music generation.
method Interleaving event and control sequences to predict future events.
result Anticipatory model matches autoregressive models in performance and can infill control tasks.
Reinforcement learning controls complex, black-boxed systems like greenhouses.
problem Controlling nonlinear, complex, and black-boxed systems.
method Actor-critic reinforcement learning approach.
result Successfully maintained greenhouse conditions for 20 times longer than other methods.
Meta-learning control algorithm with finite-time guarantees for unknown systems.
problem Online control of unknown linear systems with constraints.
method Provable regret guarantees for an iterative control algorithm.
result Regret bounds of O(T3/4) for controller cost and constraint violation. New algorithm achieves logarithmic regret for adversarial online control.
problem Online linear-quadratic control in systems with adversarial disturbances.
method Characterization of optimal offline control law, reduced to online learning with approximate advantage functions.
result First algorithm with logarithmic regret for arbitrary adversarial disturbance sequences.
Designs adaptive controller for networked control systems with wireless data transmission.
problem Adaptive control in networked systems with unreliable wireless channels.
method Upper Confidence Bounds for Networked Control Systems (UCB-NCS) learning rule.
result Non-asymptotic performance guarantees with a regret bound of O(C√T).
New robust control method for uncertain systems using bootstrapped noise.
problem Designing controllers robust to model uncertainties in finite data.
method Least-squares model estimator, bootstrap resampling, multiplicative noise LQR.
result Significantly outperforms certainty equivalent controllers in numerical tests.
Since governments give stimulus to firms and expect the spillover effect by fiscal policies, it is important to know the effectiveness that they can control the economy. To clarify the controllability of the economy, we investigate a firm production network observed exhaustively in Japan and what firms should be direct…
This dissertation uses deep reinforcement learning to improve drone flight control.
problem Inadequate traditional control methods for unpredictable CPS interactions.
method Developed a full solution stack for neuro-flight controllers using deep neural networks.
result Reinforcement learning enables training neural network controllers for stable and precise flight.