arXiv research

Meta-reinforcement learning improves fault-adaptive control efficiency.

Deep reinforcement learning controls drones without model knowledge.

Hybrid controller combines model-based and policy-based reinforcement learning.

Paper uses deep reinforcement learning for better control of rocket engines during start-up phases.

A decentralized deep RL controller improves hexapod locomotion learning.

A reinforcement learning approach prepares quantum squeezed states in open spin systems.

FinFlowRL combines imitation and reinforcement learning for better financial control.

Continuous reinforcement learning such as DDPG and A3C are widely used in robot control and autonomous driving. However, both methods have theoretical weaknesses. While DDPG cannot control noises in the control process, A3C does not satisfy the continuity conditions under the Gaussian policy. To address these concerns,…

RL applied to TCLs for power consumption control.

Adaptive traffic control uses deep RL to improve decision-making.

This paper uses deep reinforcement learning to automate electric transmission voltage control.

Novel Bayesian meta-reinforcement learning framework improves traffic signal control robustness.

Automates bias control in reinforcement learning algorithms.

Survey of theoretical foundations for policy optimization in control.

New framework for policy gradient methods in continuous time reinforcement learning.

Safe RL in linear systems achieves $\sqrt{T}$-regret.

Study uses multi-agent reinforcement learning to control self-assembly with high-resolution external control.

This manuscript surveys reinforcement learning from the perspective of optimization and control with a focus on continuous control applications. It surveys the general formulation, terminology, and typical experimental implementations of reinforcement learning and reviews competing solution paradigms. In order to compa…

Combining causality, control, and reinforcement learning for system control.

The framework of reinforcement learning or optimal control provides a mathematical formalization of intelligent decision making that is powerful and broadly applicable. While the general form of the reinforcement learning problem enables effective reasoning about uncertainty, the connection between reinforcement learni…

Deep RL controller outperforms market making benchmarks in a Hawkes process model.

CURL uses contrastive learning to improve reinforcement learning performance.

Paper proposes Vertex Networks for reinforcement learning of control systems with safety guarantees.

Paper uses RL for high-level character control in 3D environments.

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…

A new reinforcement learning method for robots thinking and moving simultaneously.

RL models improve target control in SSGs for security applications.

The OGY method is one of control methods for a chaotic system. In the method, we have to calculate a stabilizing periodic orbit embedded in its chaotic attractor. Thus, we cannot use this method in the case where a precise mathematical model of the chaotic system cannot be identified. In this case, the delayed feedback…

Study shows how to control jump-diffusion processes with stable feedback controls in reinforcement learning.

A new reinforcement learning method reduces action complexity for robust control.

Many real-world control problems involve both discrete decision variables - such as the choice of control modes, gear switching or digital outputs - as well as continuous decision variables - such as velocity setpoints, control gains or analogue outputs. However, when defining the corresponding optimal control or reinf…

A framework for robust exploration in reinforcement learning under ambiguity.

Variable speed limits (VSL) control is a flexible way to improve traffic condition,increase safety and reduce emission. There is an emerging trend of using reinforcement learning technique for VSL control and recent studies have shown promising results. Currently, deep learning is enabling reinforcement learning to dev…

FinFlowRL learns from experts to optimize financial control in changing markets.

Unified reinforcement learning and stochastic processes with action-driven processes.

This paper improves MARL for networked systems through new protocols and discount factors.

We study a security threat to batch reinforcement learning and control where the attacker aims to poison the learned policy. The victim is a reinforcement learner / controller which first estimates the dynamics and the rewards from a batch data set, and then solves for the optimal policy with respect to the estimates. …

Paper proposes a DRL-based controller for networked AP systems that reduces communication frequency.

MVPI framework optimizes risk in reinforcement learning, improving performance in robot simulations.

A new approach to reinforcement learning improves policy performance by adjusting control frequency.

RL solves discrete LQ control with Gaussian optimal policy.

Study uses deep reinforcement learning for real-time control of nuclear microreactors, achieving similar or superior performance to traditional PID controllers.

A key challenge for gradient based optimization methods in model-free reinforcement learning is to develop an approach that is sample efficient and has low variance. In this work, we apply Kronecker-factored curvature estimation technique (KFAC) to a recently proposed gradient estimator for control variate optimization…

A language for specifying complex reinforcement learning tasks.

Paper proposes a deep RL approach for traffic signal control balancing efficiency and equity.

Despite the numerous advances, reinforcement learning remains away from widespread acceptance for autonomous controller design as compared to classical methods due to lack of ability to effectively tackle the reality gap. The reliance on absolute or deterministic reward as a metric for optimization process renders rein…

We introduce a control-tutored reinforcement learning (CTRL) algorithm. The idea is to enhance tabular learning algorithms so as to improve the exploration of the state-space, and substantially reduce learning times by leveraging some limited knowledge of the plant encoded into a tutoring model-based control strategy. …

Study uses DRL with Lagrangian relaxation to solve temporal control tasks with STL constraints.