mlsanityData to 14 Oct 2026

Bridging Reinforcement Learning and Optimal Control via Feasible Action Mapping

arXiv 2607.23930 ↗First posted 27 Jul 2026eess.SY cs.RO cs.SYcited by 0

On the map: Deep reinforcement learning methods → Safe and constrained RL

Abstract (arXiv)

Operating constrained dynamical systems requires controllers to efficiently solve complex tasks while enforcing recursive feasibility and physical 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 core 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 instantaneous parameter feasibility. When paired with invariant terminal sets, FAOC guarantees strict recursive feasibility and safe operation, effectively combining the predictable safety of OC with the behavioral flexibility of RL. Unlike prior work, the abstract action space does not require expert tuning, nor is the OCP formulation compromised by the inability of RL to guarantee feasibility. We evaluate FAOC on real-time motion planning for robot table tennis, where simulated experiments demonstrate superior sample efficiency and closed-loop performance compared to state-of-the-art baselines. We open-source the used implementation of the mapping algorithm and OCP for motion planning https://github.com/SonyResearch/feasible_action_for_optimal_control.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Safe and constrained RL, one of 15 directions in Deep reinforcement learning methods. Builds on 25 of its 50 references that are in the map. First posted on arXiv 27 Jul 2026.

Builds on

25 of 50 references.

References · 25

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  2. 2021Convex optimizationcited by 2,515
  3. 2019Learning agile and dynamic motor skills for legged robotscited by 504
  4. 2024Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learningcited by 189
  5. 2023ANYmal Parkour: Learning Agile Navigation for Quadrupedal Robotscited by 152
  6. 2024Stop Regressing: Training Value Functions via Classification for Scalable Deep RLcited by 144
  7. 2018Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Controlcited by 113
  8. 2024Bigger, Regularized, Optimistic: scaling for compute and sample-efficient continuous controlcited by 108
  9. 20251000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilitiescited by 45
  10. 2025Hyperspherical Normalization for Scalable Deep Reinforcement Learningcited by 38
  11. 2021Data-Driven MPC for Quadrotorscited by 35
  12. 2020Safe Reinforcement Learning via Projection on a Safe Set: How to Achieve Optimality?cited by 34
13 more
  1. 2021Where to go next: Learning a Subgoal Recommendation Policy for Navigation Among Pedestrianscited by 28
  2. 2025Synthesis of Model Predictive Control and Reinforcement Learning: Survey and Classificationcited by 26
  3. 2021Safe Reinforcement Learning with Chance-constrained Model Predictive Controlcited by 20
  4. 2019Learning When to Drive in Intersections by Combining Reinforcement Learning and Model Predictive Controlcited by 9
  5. 2025Inverse Optimization via Learning Feasible Regionscited by 8
  6. 2022A Hierarchical Approach for Strategic Motion Planning in Autonomous Racingcited by 7
  7. 2024A Safe Reinforcement Learning driven Weights-varying Model Predictive Control for Autonomous Vehicle Motion Controlcited by 7
  8. 2023Adaptive Stochastic Nonlinear Model Predictive Control with Look-ahead Deep Reinforcement Learning for Autonomous Vehicle Motion Controlcited by 6
  9. 2020Learning Robot Trajectories subject to Kinematic Joint Constraintscited by 5
  10. 2021Intrinsic Benefits of Categorical Distributional Loss: Uncertainty-aware Regularized Exploration in Reinforcement Learningcited by 5
  11. 2024Action Mapping for Reinforcement Learning in Continuous Environments with Constraintscited by 5
  12. 2021A Dual Active-Set Solver for Embedded Quadratic Programming Using Recursive LDL' Updatescited by 4
  13. 2024Optimal Transportation by Orthogonal Coupling Dynamicscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026A Decade of Bayesian Optimization for Controller Tuning and Robot Learning: Tutorial, Review, and Future Prospects
  2. 2025A Review of Learning-Based Motion Planning: Toward a Data-Driven Optimal Control Approach
  3. 2024Bridging the gap between Learning-to-plan, Motion Primitives and Safe Reinforcement Learning
  4. 2025Taxonomy and Trends in Reinforcement Learning for Robotics and Control Systems: A Structured Review
  5. 2026Foundations of Reinforcement Learning and Control:Connections and New Perspectives
  6. 2024The Feasibility Theory of Constrained Reinforcement Learning: A Tutorial Study
  7. 2026From Kinematics to Dynamics: Learning to Refine Hybrid Plans for Physically Feasible Execution
  8. 2026Model-Based Diffusion Optimal Control for Multi-Robot Motion Planning