Bridging Reinforcement Learning and Optimal Control via Feasible Action Mapping

• URL: http://arxiv.org/abs/2607.23930v1
• Date: Mon, 27 Jul 2026 02:01:14 GMT
• Title: Bridging Reinforcement Learning and Optimal Control via Feasible Action Mapping
• Abstract summary: We present a novel control framework integrating Reinforcement Learning (RL) and Optimal Control (OC)<n>FAOC effectively combines the predictable safety of OC with the flexibility of RL.<n>We show that FAOC outperforms state-of-the-art baselines in both sample efficiency and closed-loop performance.
• Score: 1.0302433430544693
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Operating constrained dynamical systems requires controllers to efficiently solve complex tasks while enforcing recursive feasibility and safety constraints. To address these competing requirements, we present Feasible Action for Optimal Control (FAOC), a novel control framework integrating Reinforcement Learning (RL) and Optimal Control (OC). The key contribution is a computationally efficient, optimization-based mapping algorithm that transforms the RL agent's action from a static abstract set into a state-dependent feasible parameter set of the Optimal Control Problem (OCP), guaranteeing strict satisfaction of the dynamical system's constraints. Thus, FAOC effectively combines the predictable safety of OC with the flexibility of RL. In contrast to prior work, the abstract action space of the RL agent does not require expert or heuristic design, and the OCP formulation is not compromised by the inability of RL to guarantee feasibility. We apply our approach to real-time motion planning for robot table tennis, which encapsulates these challenges. Via simulated experiments, we show that FAOC outperforms state-of-the-art baselines in both sample efficiency and closed-loop performance.

Related papers

• Joint Air Traffic Flow and Capacity Management via Answer Set Programming [64.47906587579985]
  We introduce a joint ATFCM model with an encoding in Answer Set Programming (ASP)<n>Our results indicate that the ASP model outperforms the MIP model.<n>While DAC has the largest improvement on solving performance compared to rerouting, unrestricted variants of DAC or rerouting lead to search space thrashing.
  arXiv  Detail & Related papers  (2026-06-22T07:58:54Z)
• LaST-R1: Reinforcing Robotic Manipulation via Adaptive Physical Latent Reasoning [90.86828952599147]
  We present LaST-R1, a novel reinforcement learning framework designed to harness "latent reasoning-before-acting" policies.<n>LaST-R1 achieves a near-perfect 99.9% average success rate on the LIBERO benchmark.<n>In real-world deployments, LaST-R1 yields up to a 22.5% average improvement over SOTA supervised fine-tuning approach.
  arXiv  Detail & Related papers  (2026-04-30T17:59:52Z)
• Growing Q-Networks: Solving Continuous Control Tasks with Adaptive Control Resolution [51.83951489847344]
  In robotics applications, smooth control signals are commonly preferred to reduce system wear and energy efficiency. In this work, we aim to bridge this performance gap by growing discrete action spaces from coarse to fine control resolution. Our work indicates that an adaptive control resolution in combination with value decomposition yields simple critic-only algorithms that yield surprisingly strong performance on continuous control tasks.
  arXiv  Detail & Related papers  (2024-04-05T17:58:37Z)
• Reinforcement Learning-based Receding Horizon Control using Adaptive Control Barrier Functions for Safety-Critical Systems [14.166970599802324]
  Optimal control methods provide solutions to safety-critical problems but easily become intractable.<n>We propose a Reinforcement Learning-based Receding Horizon Control approach leveraging Model Predictive Control.<n>We validate our method by applying it to the challenging automated merging control problem for Connected and Automated Vehicles.
  arXiv  Detail & Related papers  (2024-03-26T02:49:08Z)
• Hybrid Reinforcement Learning for Optimizing Pump Sustainability in Real-World Water Distribution Networks [55.591662978280894]
  This article addresses the pump-scheduling optimization problem to enhance real-time control of real-world water distribution networks (WDNs) Our primary objectives are to adhere to physical operational constraints while reducing energy consumption and operational costs. Traditional optimization techniques, such as evolution-based and genetic algorithms, often fall short due to their lack of convergence guarantees.
  arXiv  Detail & Related papers  (2023-10-13T21:26:16Z)
• A Constraint Enforcement Deep Reinforcement Learning Framework for Optimal Energy Storage Systems Dispatch [0.0]
  The optimal dispatch of energy storage systems (ESSs) presents formidable challenges due to fluctuations in dynamic prices, demand consumption, and renewable-based energy generation. By exploiting the generalization capabilities of deep neural networks (DNNs), deep reinforcement learning (DRL) algorithms can learn good-quality control models that adaptively respond to distribution networks' nature. We propose a DRL framework that effectively handles continuous action spaces while strictly enforcing the environments and action space operational constraints during online operation.
  arXiv  Detail & Related papers  (2023-07-26T17:12:04Z)
• Evaluating Model-free Reinforcement Learning toward Safety-critical Tasks [70.76757529955577]
  This paper revisits prior work in this scope from the perspective of state-wise safe RL. We propose Unrolling Safety Layer (USL), a joint method that combines safety optimization and safety projection. To facilitate further research in this area, we reproduce related algorithms in a unified pipeline and incorporate them into SafeRL-Kit.
  arXiv  Detail & Related papers  (2022-12-12T06:30:17Z)
• Safe-Critical Modular Deep Reinforcement Learning with Temporal Logic through Gaussian Processes and Control Barrier Functions [3.5897534810405403]
  Reinforcement learning (RL) is a promising approach and has limited success towards real-world applications. In this paper, we propose a learning-based control framework consisting of several aspects. We show such an ECBF-based modular deep RL algorithm achieves near-perfect success rates and guard safety with a high probability.
  arXiv  Detail & Related papers  (2021-09-07T00:51:12Z)
• Constrained Model-Free Reinforcement Learning for Process Optimization [0.0]
  Reinforcement learning (RL) is a control approach that can handle nonlinear optimal control problems. Despite the promise exhibited, RL has yet to see marked translation to industrial practice. We propose an 'oracle'-assisted constrained Q-learning algorithm that guarantees the satisfaction of joint chance constraints with a high probability.
  arXiv  Detail & Related papers  (2020-11-16T13:16:22Z)
• Guided Constrained Policy Optimization for Dynamic Quadrupedal Robot Locomotion [78.46388769788405]
  We introduce guided constrained policy optimization (GCPO), an RL framework based upon our implementation of constrained policy optimization (CPPO) We show that guided constrained RL offers faster convergence close to the desired optimum resulting in an optimal, yet physically feasible, robotic control behavior without the need for precise reward function tuning.
  arXiv  Detail & Related papers  (2020-02-22T10:15:53Z)
• Discrete Action On-Policy Learning with Action-Value Critic [72.20609919995086]
  Reinforcement learning (RL) in discrete action space is ubiquitous in real-world applications, but its complexity grows exponentially with the action-space dimension. We construct a critic to estimate action-value functions, apply it on correlated actions, and combine these critic estimated action values to control the variance of gradient estimation. These efforts result in a new discrete action on-policy RL algorithm that empirically outperforms related on-policy algorithms relying on variance control techniques.
  arXiv  Detail & Related papers  (2020-02-10T04:23:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.