New risk control method for non-monotonic losses in complex parameters.
problem Controlling risk for non-monotonic losses with multidimensional parameters.
method Stability-based guarantees for generic algorithms applied to non-monotonic losses.
result Guarantees depend on algorithm stability, with looser guarantees for unstable algorithms.
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.
Langevin algorithms enhance training of deep neural networks for stochastic control problems.
problem Training acceleration for deep neural networks in stochastic control problems.
method Application of Langevin algorithms to minimize the loss of deep neural networks in stochastic control problems.
result Langevin algorithms improve training on various stochastic control problems.
New algorithms control FDX while achieving more power in online multiple testing.
problem Problems with previous online multiple testing methods, including high FDX and low power.
method Developed new dynamic algorithms that adjust testing levels based on accumulated wealth.
result SupLORD algorithm achieves higher power and FDR control in synthetic experiments.
Reinforcement Learning (RL) algorithms have found limited success beyond simulated applications, and one main reason is the absence of safety guarantees during the learning process. Real world systems would realistically fail or break before an optimal controller can be learned. To address this issue, we propose a cont…
Generalising the idea of the classical EM algorithm that is widely used for computing maximum likelihood estimates, we propose an EM-Control (EM-C) algorithm for solving multi-period finite time horizon stochastic control problems. The new algorithm sequentially updates the control policies in each time period using Mo…
Optimizes control of noisy discrete systems without system matrix knowledge.
problem Optimal control of discrete-time systems with additive and multiplicative noises.
method Stochastic Lyapunov and Riccati equations, model-free reinforcement learning.
result Model-free reinforcement learning algorithm converges to optimal control policy.
New algorithm controls systems with unknown, changing losses.
problem Control systems with adversarial perturbations and unknown loss function.
method Efficient sublinear regret algorithm for bandit convex optimization with memory.
result Achieves efficient control with sublinear regret in the presence of unknown, changing losses.
CTRL improves reinforcement learning by combining control strategies.
problem Controlling agents to herd and contain target agents in a goal region.
method CTRL algorithm that enhances tabular learning algorithms with a tutoring model-based control strategy.
result Significantly reduces learning times and improves exploration of the state-space.
New RL algorithms improve control tasks with data reuse.
problem Real-world control requires performance guarantees and data efficiency.
method Generalized Policy Improvement combining on-policy guarantees and sample reuse.
result Extensive experimental analysis shows benefits of new algorithms.
Editorial discusses nine challenges in modern algorithmic trading.
problem Challenges in modern algorithmic trading and controls.
method Discussion of challenges without proposing solutions.
result No specific new results or findings.
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 ( T 3 / 4 ) O(T^{3/4}) O ( T 3/4 ) for controller cost and constraint violation. Proposes a model-free control method for chaotic systems using deep Q-learning.
problem Chaos control in systems without precise mathematical models.
method Data-based control policy with two steps: region determination and policy learning.
result Efficient control policy learning in a limited region of state space.
Paper formulates EnKF as optimal transport problem for unique control law.
problem Unique control law for EnKF algorithms.
method Formulated as optimal transportation problem, derived explicit control law.
result Mean squared error converges to zero with finite particles.
A number of optimal decision problems with uncertainty can be formulated into a stochastic optimal control framework. The Least-Squares Monte Carlo (LSMC) algorithm is a popular numerical method to approach solutions of such stochastic control problems as analytical solutions are not tractable in general. This paper ge…
Two clustering algorithms optimize edge controller placement in wireless networks.
problem Optimizing edge controller placement in wireless edge networks.
method Deterministic annealing based clustering algorithms ECP-LL and ECP-LB.
result The algorithms achieve better balance between synchronization and delay costs.
Paper proposes an intersection decision algorithm for autonomous vehicles.
problem Navigating intersections with non-automated vehicles.
method Combines reinforcement learning for high-level decisions and model predictive control for low-level planning.
result The proposed algorithm outperforms another controller in success rate and training episodes.
This paper presents several numerical applications of deep learning-based algorithms that have been introduced in [HPBL18]. Numerical and comparative tests using TensorFlow illustrate the performance of our different algorithms, namely control learning by performance iteration (algorithms NNcontPI and ClassifPI), contr…
We study Bayesian optimal control of a general class of smoothly parameterized Markov decision problems. Since computing the optimal control is computationally expensive, we design an algorithm that trades off performance for computational efficiency. The algorithm is a lazy posterior sampling method that maintains a d…
A new ML algorithm solves complex economic control problems.
problem Solving high-dimensional, finite-horizon stochastic control problems in economics.
method Deep neural network representation of optimal policy functions with three key features.
result Efficiently solves various economic control problems including recursive utility and growth models.
A method to minimize regret in multi-agent control systems with adversarial disturbances.
problem Optimal control of dynamical systems with adversarial disturbances and multiple agents.
method Reduction from online convex optimization to a distributed algorithm for multi-agent control.
result The resulting distributed algorithm has low regret relative to the optimal precomputed joint policy.
Algorithm reduces control regret for unknown systems.
problem Minimizing control regret for unknown linear systems.
method Novel geometric exploration strategy and polynomial-time algorithms.
result First polynomial-time algorithms with optimal regret bounds.
Automates bias control in reinforcement learning algorithms.
problem Overestimation bias in reinforcement learning algorithms.
method Data-driven approach for automatic selection of bias control hyperparameters.
result Significant reduction in the number of interactions while maintaining performance.
New online learning algorithms improve cyberattack detection in industrial control systems.
problem Detecting cyberattacks in industrial control systems with limited resources.
method Online learning algorithms to process continuous data streams and address class imbalance.
result Improved detection rate of cyberattacks in industrial control systems.
Differentially private synthetic control estimates treatment effects while protecting privacy.
problem Estimating treatment effects on sensitive data without revealing individual information.
method Combines non-private synthetic control and differentially private empirical risk minimization.
result Private synthetic control produces accurate predictions with minimal privacy cost.
Efficient algorithm controls unknown systems with adversarial perturbations.
problem Controlling unknown linear systems with adversarial perturbations and convex losses.
method Measures regret against an optimal linear policy, provides efficient algorithm with sublinear regret bound.
result First efficient algorithm with sublinear regret bound of T^{2/3}.
New algorithm minimizes worst-case regret in uncertain, time-varying dynamics.
problem Model-based policy learning in uncertain, time-varying dynamics.
method Planning regret metric and iterative algorithm for minimizing it.
result Empirical evidence shows the proposed algorithm outperforms existing methods.
The paper optimizes policies constrained to Schur stabilizing controllers using a Newton-type algorithm.
problem Optimizing policies under linear constraints in control systems.
method Newton-type algorithm on a manifold of Schur stabilizing controllers with a Riemannian metric.
result Local convergence guarantees for the Newton-type algorithm without relying on exponential mapping or retractions.
Paper proposes a new method for learning latent representations for control problems.
problem Learning representations for control algorithms in high-dimensional observation spaces.
method Formulated a loss function (PCC) consisting of prediction, consistency, and curvature terms, derived an amortized variational bound.
result The new variational-PCC learning algorithm leads to superior control performance and more stable training.
Nonlinear optimal control problems are often solved with numerical methods that require knowledge of system's dynamics which may be difficult to infer, and that carry a large computational cost associated with iterative calculations. We present a novel neurobiologically inspired hierarchical learning framework, Reinfor…
We geometrically describe optimal control problems in terms of Morse families in the Hamiltonian framework. These geometric structures allow us to recover the classical first order necessary conditions for optimality and the starting point to run an integrability algorithm. Moreover the integrability algorithm is adapt…
dtControl uses decision trees to represent controllers efficiently and explainably.
problem Representing controllers concisely and explainably.
method dtControl uses decision tree learning algorithms to represent controllers. Novel techniques for determinizing controllers are introduced.
result Novel techniques for determinizing controllers during decision tree construction are extremely efficient, yielding small decision trees.
Improved confidence interval estimation with control variates.
problem Estimating confidence intervals with minimal samples.
method Designing an estimation algorithm using control variates and leveraging order statistics.
result Improved asymptotic efficiency compared to existing algorithms.
Paper proves deep learning method for stochastic control converges and outperforms existing algorithms.
problem Formulating and solving stochastic control problems using FBSDE and SMP.
method Deep learning algorithm based on SMP, with convergence proof and error bounds.
result Deep SMP-BSDE algorithm converges and outperforms existing methods in high-dimensional stochastic control problems.
RL models improve target control in SSGs for security applications.
problem Improving RL algorithms for target control in SSGs.
method Investigates improvements to target representations in RL algorithms.
result Enhanced RL models control targets better in SSGs.
The paper develops online methods to control familywise error rate in growing hypothesis testing sequences.
problem Controlling familywise error rate in a growing sequence of hypotheses over time.
method Unified algorithmic concepts for offline and online FWER control, including new adaptive online algorithms.
result Substantial gains in power demonstrated and formally proved in a Gaussian sequence model.
Adaptive traffic control uses deep RL to improve decision-making.
problem Improving traffic control using deep RL.
method Integrates recent deep RL techniques into a novel DQN-based algorithm (TC-DQN+) for traffic control.
result Proposes a new reward function for traffic control.
New algorithm uses control variates to improve multi-armed bandit performance.
problem Stochastic multi-armed bandits with auxiliary reward information.
method Developed UCB-CV algorithm using control variates for mean estimation.
result UCB-CV algorithm provides tighter confidence bounds and smaller variance.
Extends conformal prediction for controlling expected risk of monotone loss functions.
problem Controlling expected risk of monotone loss functions.
method Generalizes split conformal prediction with coverage guarantee, extending to distribution shift, quantile risk, multiple, adversarial, and expectations of U-statistics.
result Tight up to an O ( 1 / n ) \mathcal{O}(1/n) O ( 1/ n ) factor, with worked examples in computer vision and natural language processing. Study shows how to control jump-diffusion processes with stable feedback controls in reinforcement learning.
problem Control jump-diffusion processes with unknown coefficients in reinforcement learning.
method Lipschitz continuous optimal feedback controls, stability analysis of forward-backward SDEs, least-squares algorithm.
result Achieves O ( N ln N ) O(\sqrt{N\ln N}) O ( N ln N ) regret for linear-convex learning problems with jumps. The paper solves complex control problems using neural networks.
problem Solving McKean-Vlasov control problems.
method Mean-field neural networks and algorithms based on dynamic programming and stochastic maximum principle.
result Extensive numerical results show the accuracy of the proposed algorithms.
DMPC combines MPC and value function estimation for efficient control tasks.
problem Efficiently solve control tasks with sparse and binary reward signals.
method Actor-critic algorithm combining MPC and value function estimation.
result DMPC actor minimizes an upper bound of cross-entropy to optimal policy.
This work frames active inference through control as inference, offering robust control algorithms.
problem Active inference framework lacks practical sensorimotor control algorithms.
method Frame active inference through control as inference, presenting trajectory optimization as inference.
result AI may be framed as partially-observed CaI when the cost function is defined in observation states.
Algorithm optimizes system design and control for better rewards.
problem Optimizing system design and control for maximum rewards.
method Deep reinforcement learning combining policy gradient and model-based optimization.
result DEPS algorithm outperforms state-of-the-art methods in various environments.
Paper proposes CARL for better control in RL from sensory data.
problem Efficient control of complex systems from high-dimensional sensory inputs.
method Control-Aware Representation Learning (CARL) for model-based RL.
result CARL improves control performance in benchmark tasks.
Classical methods to control heating systems are often marred by suboptimal performance, inability to adapt to dynamic conditions and unreasonable assumptions e.g. existence of building models. This paper presents a novel deep reinforcement learning algorithm which can control space heating in buildings in a computatio…
New algorithm reduces control error in systems with changing dynamics.
problem Online control of systems with time-varying linear dynamics.
method Introduces adaptive regret metric and a novel meta-algorithm.
result First adaptive regret bound for online convex optimization with memory.
This paper addresses the problem of learning the optimal control policy for a nonlinear stochastic dynamical system with continuous state space, continuous action space and unknown dynamics. This class of problems are typically addressed in stochastic adaptive control and reinforcement learning literature using model-b…