CACTO-BIC: Scalable Actor-Critic Learning via Biased Sampling and GPU-Accelerated Trajectory Optimization

• URL: http://arxiv.org/abs/2602.19699v1
• Date: Mon, 23 Feb 2026 10:45:36 GMT
• Title: CACTO-BIC: Scalable Actor-Critic Learning via Biased Sampling and GPU-Accelerated Trajectory Optimization
• Abstract summary: Tray Comparison Optimization (TO) and Reinforcement Learning (RL) offer strengths for optimal control problems.<n>TO efficiently computes locally while CACGO is more robust to struggle with high-dimensional challenges.
• Score: 1.9644272536912284
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Trajectory Optimization (TO) and Reinforcement Learning (RL) offer complementary strengths for solving optimal control problems. TO efficiently computes locally optimal solutions but can struggle with non-convexity, while RL is more robust to non-convexity at the cost of significantly higher computational demands. CACTO (Continuous Actor-Critic with Trajectory Optimization) was introduced to combine these advantages by learning a warm-start policy that guides the TO solver towards low-cost trajectories. However, scalability remains a key limitation, as increasing system complexity significantly raises the computational cost of TO. This work introduces CACTO-BIC to address these challenges. CACTO-BIC improves data efficiency by biasing initial-state sampling leveraging a property of the value function associated with locally optimal policies; moreover, it reduces computation time by exploiting GPU acceleration. Empirical evaluations show improved sample efficiency and faster computation compared to CACTO. Comparisons with PPO demonstrate that our approach can achieve similar solutions in less time. Finally, experiments on the AlienGO quadruped robot demonstrate that CACTO-BIC can scale to high-dimensional systems and is suitable for real-time applications.

Related papers

• Convex Optimization for Alignment and Preference Learning on a Single GPU [52.997197698288936]
  Fine-tuning large language models to align with human preferences has driven the success of systems such as Gemini and ChatGPT.<n>Direct Preference Optimization (DPO) offers a simpler alternative but has limitations such as inconsistent ranking accuracy and high dependence on GPU resources.<n>We propose the Convex Optimization for Alignment and Preference Learning Algorithm (COALA), a novel lightweight strategy with strong theoretical guarantees.
  arXiv  Detail & Related papers  (2026-05-22T05:25:00Z)
• Breaking the Computational Barrier: Provably Efficient Actor-Critic for Low-Rank MDPs [53.412166189410904]
  We use supervised learning as a computational proxy to establish a hierarchy of commonly adopted RL oracles under low-rank Markov Decision Processes (MDPs)<n>Motivated by this observation, we propose a novel optimistic actor-critic algorithm that relies solely on the policy evaluation oracle.<n>We prove that our algorithm outperforms the existing sample complexity guarantees for low-rank MDPs while avoiding computationally expensive planning or optimization oracles commonly assumed in prior works.
  arXiv  Detail & Related papers  (2026-05-02T04:46:54Z)
• Preference Optimization for Combinatorial Optimization Problems [54.87466279363487]
  Reinforcement Learning (RL) has emerged as a powerful tool for neural optimization, enabling models learns that solve complex problems without requiring expert knowledge.<n>Despite significant progress, existing RL approaches face challenges such as diminishing reward signals and inefficient exploration in vast action spaces.<n>We propose Preference Optimization, a novel method that transforms quantitative reward signals into qualitative preference signals via statistical comparison modeling.
  arXiv  Detail & Related papers  (2025-05-13T16:47:00Z)
• WARP-LCA: Efficient Convolutional Sparse Coding with Locally Competitive Algorithm [1.4186974630564675]
  We show that WARP-LCA converges faster by orders of magnitude and reaches better minima compared to conventional LCA.<n>We demonstrate that WARP-LCA exhibits superior properties in terms of reconstruction and denoising quality as well as robustness when applied in deep recognition pipelines.
  arXiv  Detail & Related papers  (2024-10-24T14:47:36Z)
• CACTO-SL: Using Sobolev Learning to improve Continuous Actor-Critic with Trajectory Optimization [12.115023915042617]
  Trabo learning guide TO and Reinforcement Learning (RL) are powerful tools to solve optimal control problems. In this work, we present an extension of CACTO exploiting the idea of Solev-SL.
  arXiv  Detail & Related papers  (2023-12-17T09:44:41Z)
• Federated Conditional Stochastic Optimization [110.513884892319]
  Conditional optimization has found in a wide range of machine learning tasks, such as in-variant learning tasks, AUPRC, andAML. This paper proposes algorithms for distributed federated learning.
  arXiv  Detail & Related papers  (2023-10-04T01:47:37Z)
• Controlling Continuous Relaxation for Combinatorial Optimization [0.0]
  Unsupervised learning solvers for optimization (CO) train a neural network that generates a soft solution using a continuous relaxation strategy. This study introduces a Continuous Relaxation Anneal (CRA) strategy, an effective-free learning method for UL-based solvers.
  arXiv  Detail & Related papers  (2023-09-29T04:23:58Z)
• Asymptotically Unbiased Instance-wise Regularized Partial AUC Optimization: Theory and Algorithm [101.44676036551537]
  One-way Partial AUC (OPAUC) and Two-way Partial AUC (TPAUC) measures the average performance of a binary classifier. Most of the existing methods could only optimize PAUC approximately, leading to inevitable biases that are not controllable. We present a simpler reformulation of the PAUC problem via distributional robust optimization AUC.
  arXiv  Detail & Related papers  (2022-10-08T08:26:22Z)
• Fast Distributionally Robust Learning with Variance Reduced Min-Max Optimization [85.84019017587477]
  Distributionally robust supervised learning is emerging as a key paradigm for building reliable machine learning systems for real-world applications. Existing algorithms for solving Wasserstein DRSL involve solving complex subproblems or fail to make use of gradients. We revisit Wasserstein DRSL through the lens of min-max optimization and derive scalable and efficiently implementable extra-gradient algorithms.
  arXiv  Detail & Related papers  (2021-04-27T16:56:09Z)
• Combining Deep Learning and Optimization for Security-Constrained Optimal Power Flow [94.24763814458686]
  Security-constrained optimal power flow (SCOPF) is fundamental in power systems. Modeling of APR within the SCOPF problem results in complex large-scale mixed-integer programs. This paper proposes a novel approach that combines deep learning and robust optimization techniques.
  arXiv  Detail & Related papers  (2020-07-14T12:38:21Z)
• High Dimensional Bayesian Optimization Assisted by Principal Component Analysis [4.030481609048958]
  We introduce a novel PCA-assisted BO (PCA-BO) algorithm for high-dimensional numerical optimization problems. We show that PCA-BO can effectively reduce the CPU time incurred on high-dimensional problems, and maintains the convergence rate on problems with an adequate global structure.
  arXiv  Detail & Related papers  (2020-07-02T07:03:27Z)

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.