This paper proposes a system-agnostic policy for dynamic scheduling.
problem Dynamic scheduling in changing systems is challenging due to system-specific optimal policies.
method Descriptive policy that learns a system-agnostic scheduling principle.
result System-agnostic meta-learning enables adaptation to unseen system characteristics.
The paper provides a non-asymptotic error bound for linear system identification under nonlinear policies.
problem System identification for linear systems with nonlinear and/or time-varying policies under i.i.d. random excitation noises.
method Least square estimation with non-asymptotic error bound for bounded state and action trajectories.
result The error bound is consistent with linear policies and generalizes existing guarantees.
Policy gradient converges to globally optimal policy in nearly linear-quadratic systems.
problem Finding optimal policies in nonlinear control systems with partial information.
method Policy gradient algorithm designed for nearly linear-quadratic regulators with small Lipschitz nonlinear components.
result Policy gradient algorithm converges to globally optimal policy with linear rate.
Study examines how uncertainty visualization affects analyst trust in automated classification systems.
problem The impact of uncertainty on analyst trust in automated classification systems.
method Empirical study evaluating different active learning query policies and visualizations.
result Query policy significantly influences analyst trust in automated classification systems.
Sayer uses implicit feedback to optimize system policies.
problem Leveraging implicit feedback to improve system policies is difficult due to bias and incompleteness.
method Sayer combines randomized exploration and unbiased counterfactual estimators to evaluate and train new policies using implicit feedback.
result Sayer can accurately evaluate and train new policies that outperform existing ones.
Faster policy learning via continuous-time gradients.
problem Efficiently estimating policy gradients for continuous-time systems.
method Approximating continuous-time gradients directly, using adaptive discretization.
result More efficient policy gradient estimator leads to faster learning.
MA-COPP predicts multi-agent system outcomes using data from a different policy, with probabilistic guarantees.
problem Predicting outcomes in multi-agent systems using data from a different policy.
method Conformal prediction framework applied to multi-agent systems, avoiding exhaustive search.
result Achieves probabilistic guarantees for multi-agent system predictions.
Model-Based Offline Planning (MBOP) learns models from offline data to control systems directly.
problem Training RL policies from offline data without direct system interaction.
method Generates models from offline data and uses planning to control the system.
result Near-optimal policies found for simulated systems with minimal real-time interaction.
Meta-reinforcement learning improves fault-adaptive control efficiency.
problem Adaptive control under abrupt system faults with strict time constraints.
method Model-agnostic meta learning (MAML) with a fault library of prior policies.
result Improved sample efficiency and quick adaptation to new faults.
Study designs logging policies to minimize off-policy evaluation error.
problem Minimizing OPE error with logging policies for target policies.
method Characterizes reward-coverage tradeoff, proposes a unifying framework, derives optimal policies.
result Provides actionable guidance for firms choosing recommendation systems.
The H∞ control design problem is considered for nonlinear systems with unknown internal system model. It is known that the nonlinear H∞ control problem can be transformed into solving the so-called Hamilton-Jacobi-Isaacs (HJI) equation, which is a nonlinear partial differential equation that is genera…
KCRL learns stable policies for nonlinear systems with formal guarantees.
problem Lack of stabilization guarantees in RL methods for safety-critical systems.
method KCRL uses Krasovskii's Lyapunov functions as a stability constraint and a primal-dual approach to learn stabilizing policies.
result KCRL guarantees learning a stabilizing policy in a finite number of interactions.
Paper speeds up policy optimization for large recommendation systems.
problem Offline optimization of large-scale recommendation systems is computationally expensive.
method Derives an approximation of policy learning algorithms that scales logarithmically with the catalogue size.
result Our algorithm is an order of magnitude faster than naive approaches while producing equally good policies.
Study shows certainty equivalent policy minimizes regret in continuous-time systems.
problem Minimizing regret in continuous-time stochastic linear-quadratic systems.
method Theoretical analysis of randomized certainty equivalent policy.
result Establishes square-root of time regret bounds and linear scaling with parameters.
Reinforcement learning is a promising approach to learning robotics controllers. It has recently been shown that algorithms based on finite-difference estimates of the policy gradient are competitive with algorithms based on the policy gradient theorem. We propose a theoretical framework for understanding this phenomen…
In this paper, two Q-learning (QL) methods are proposed and their convergence theories are established for addressing the model-free optimal control problem of general nonlinear continuous-time systems. By introducing the Q-function for continuous-time systems, policy iteration based QL (PIQL) and value iteration based…
A new method learns physical system sensitivity to improve policy learning without needing a full model.
problem Expensive policy learning without models and model bias.
method Learn sensitivity of trajectories to parameter perturbations.
result Feasibility demonstrated on a physical robot.
The paper presents a model-free method for stabilizing unknown control systems.
problem Stabilizing unknown control systems in engineering.
method Solving discounted LQR problems with increasing discount factors.
result The method efficiently recovers a stabilizing controller for linear and smooth nonlinear systems.
Greedy policy maximizes information in unknown linear systems.
problem Exploration in unknown linear dynamical systems.
method Online greedy policy maximizing information.
result Competitive performance compared to gradient-based methods.
This paper optimizes slate decision systems for large action spaces.
problem Optimizing large-scale decision systems with arbitrary reward functions.
method A policy optimization framework with a novel relaxation of decision functions.
result Demonstrates the effectiveness of the proposed method on large action spaces.
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.
Considering a lead-time-and price-sensitive demand, we investigate whether a client rejection policy, modeled as M/M/1/K system, can be more profitable than an all-client acceptance policy, modeled as M/M/1 system. We provide analytical insights for the cases with and without holding and penalty costs by comparing M/M/…
Study online control of unknown time-varying systems with negative and positive results.
problem Online control of time-varying systems with unknown dynamics.
method Algorithmic upper bounds and lower bounds for different policy classes.
result Sublinear adaptive regret bounds for Disturbance Response policies.
Survey explores geometric aspects of policy optimization in control systems.
problem Understanding the geometric relationships between control design and optimization.
method Geometric perspective on policy optimization, focusing on parameterization and topology.
result Implications of policy geometry on stability and performance of local search algorithms.
The linear quadratic regulator (LQR) problem has reemerged as an important theoretical benchmark for reinforcement learning-based control of complex dynamical systems with continuous state and action spaces. In contrast with nearly all recent work in this area, we consider multiplicative noise models, which are increas…
CASP selects reliable policies for two-stage recommender systems by considering both value and support.
problem The selection of a generator in two-stage recommender systems affects both the policy value and the data support used to estimate it.
method CASP combines doubly robust value estimation with a support-burden penalty.
result CASP selects lower-burden policies when estimated value and support credibility are in tension.
Paper formulates mutual information optimal control for discrete-time systems.
problem Optimal control of discrete-time linear systems with mutual information.
method Formulates MIOCP as an extension of MEOCP, derives optimal policy and prior, proposes alternating minimization algorithm.
result Proposes an alternating minimization algorithm for MIOCP.
Proposes a method to estimate policy values in reinforcement learning with unmeasured confounders.
problem Estimating policy values in reinforcement learning with unmeasured confounders.
method Develops a two-way deconfounder algorithm using a neural tensor network to learn unmeasured confounders and system dynamics.
result Consistent policy value estimation through model-based estimator.
This paper addresses the model-free nonlinear optimal problem with generalized cost functional, and a data-based reinforcement learning technique is developed. It is known that the nonlinear optimal control problem relies on the solution of the Hamilton-Jacobi-Bellman (HJB) equation, which is a nonlinear partial differ…
New framework for learning policies that converge in out-of-sample regions.
problem Reliable out-of-sample recovery in imitation learning.
method Contractive dynamical systems and recurrent equilibrium networks.
result Policy rollouts converge regardless of perturbations, enabling efficient OOS recovery.
Learning optimal resource allocation policies in wireless systems can be effectively achieved by formulating finite dimensional constrained programs which depend on system configuration, as well as the adopted learning parameterization. The interest here is in cases where system models are unavailable, prompting method…
System interprets complex treatment effects for personalized policies.
problem Complex, hard-to-understand treatment effect models.
method Scalable, interpretable personalized experimentation system.
result Learned explanations and generated interpretable policies.
DiPS learns to optimize sketching policies for better recommendation quality.
problem Optimizing sketching policies for long-term user interest prediction in recommender systems.
method Differentiable policy for sketching that learns from training data.
result DiPS requires up to 50% fewer sketch items to achieve the same recommendation quality.
Industrial recommender systems deal with extremely large action spaces -- many millions of items to recommend. Moreover, they need to serve billions of users, who are unique at any point in time, making a complex user state space. Luckily, huge quantities of logged implicit feedback (e.g., user clicks, dwell time) are …
Investigates optimal pension policies in PAYG systems with forward utility and ageing population.
problem Optimal investment and pension policies in PAYG systems with sustainability and adequacy constraints.
method Non-zero volatility forward CRRA utilities, closed-form optimal policies, detailed numerical analysis.
result Characterization of optimal policies and detailed impact analysis under various scenarios.
Domain randomization (DR) is a successful technique for learning robust policies for robot systems, when the dynamics of the target robot system are unknown. The success of policies trained with domain randomization however, is highly dependent on the correct selection of the randomization distribution. The majority of…
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.
NDPs embed dynamical systems into neural networks for efficient sensorimotor learning.
problem Training policies directly in raw action spaces limits scalability for continuous tasks.
method Embed dynamical systems into neural networks to learn robot behaviors via demonstrations.
result NDPs outperform prior methods in both imitation and reinforcement learning setups.
New model-free algorithm achieves similar LQR regret guarantees.
problem Model-free control of linear dynamical systems under quadratic costs.
method Online policy gradient scheme with policy space cost analysis.
result Achieves regret scaling with √T, matching model-based methods.
Adaptive optimal control using value iteration (VI) initiated from a stabilizing policy is theoretically analyzed in various aspects including the continuity of the result, the stability of the system operated using any single/constant resulting control policy, the stability of the system operated using the evolving/ti…
Deep reinforcement learning finds optimal learning policies for adaptive systems.
problem Finding individualized learning plans for learners with unknown latent traits.
method Formulated as a Markov decision process, applied deep Q-learning with a transition model estimator.
result The algorithm efficiently discovers optimal learning policies with small data sets.
Proposes efficient algorithm for system-level I&M decisions under uncertainty.
problem Optimal management strategies for deteriorating civil engineering systems.
method Factored partially observable Markov decision process with Bayesian networks and DDMAC reinforcement learning.
result DDMAC policies offer substantial benefits over heuristic approaches in system-level cost optimization.
We consider a learning system based on the conventional multiplicative weight (MW) rule that combines experts' advice to predict a sequence of true outcomes. It is assumed that one of the experts is malicious and aims to impose the maximum loss on the system. The loss of the system is naturally defined to be the aggreg…
VRER selectively reuses samples to improve policy optimization in complex systems.
problem Lack of effective reuse of historical samples in reinforcement learning.
method Variance reduction based experience replay (VRER) framework.
result VRER accelerates policy optimization and enhances performance.
Bringing transparency to black-box decision making systems (DMS) has been a topic of increasing research interest in recent years. Traditional active and passive approaches to make these systems transparent are often limited by scalability and/or feasibility issues. In this paper, we propose a new notion of black-box D…
Develops methods to create consistent surrogate models for agent-based simulators.
problem High computational costs and misjudgment of interventions in agent-based models.
method Causal abstractions to learn interventionally consistent surrogate models.
result Surrogates trained for interventional consistency closely mimic the agent-based model's behavior under interventions.
New framework learns policies for partially observable systems.
problem Learning policies in partially observable dynamical systems.
method Partially Observable Bilinear Actor-Critic framework.
result Algorithm can learn against optimal policies in certain cases.
Control policies, trained using the Deep Reinforcement Learning, have been recently shown to be vulnerable to adversarial attacks introducing even very small perturbations to the policy input. The attacks proposed so far have been designed using heuristics, and build on existing adversarial example crafting techniques …