VisFly-Lab: Unified Differentiable Framework for First-Order Reinforcement Learning of Quadrotor Control

• URL: http://arxiv.org/abs/2603.21123v1
• Date: Sun, 22 Mar 2026 08:42:26 GMT
• Title: VisFly-Lab: Unified Differentiable Framework for First-Order Reinforcement Learning of Quadrotor Control
• Abstract summary: First-order reinforcement learning with differentiable simulation is promising for quadrotor control.<n>But practical progress remains fragmented across task-specific settings.<n>We present a unified differentiable framework for multi-task quadrotor control.
• Score: 11.762246555812554
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: First-order reinforcement learning with differentiable simulation is promising for quadrotor control, but practical progress remains fragmented across task-specific settings. To support more systematic development and evaluation, we present a unified differentiable framework for multi-task quadrotor control. The framework is wrapped, extensible, and equipped with deployment-oriented dynamics, providing a common interface across four representative tasks: hovering, tracking, landing, and racing. We also present the suite of first-order learning algorithms, where we identify two practical bottlenecks of standard first-order training: limited state coverage caused by horizon initialization and gradient bias caused by partially non-differentiable rewards. To address these issues, we propose Amended Backpropagation Through Time (ABPT), which combines differentiable rollout optimization, a value-based auxiliary objective, and visited-state initialization to improve training robustness. Experimental results show that ABPT yields the clearest gains in tasks with partially non-differentiable rewards, while remaining competitive in fully differentiable settings. We further provide proof-of-concept real-world deployments showing initial transferability of policies learned in the proposed framework beyond simulation.

Related papers

• Dual Adversarial Fine-tuning for Enhancing Robustness of Large Vision Language Model [73.59026525350808]
  We propose a dual adversarial fine-tuning framework that jointly optimize visual and semantic supervision signals from two modalities.<n>Our approach outperforms the state-of-the-art method in adversarial robustness evaluation across zero-shot classification, image captioning, and visual question answering tasks.
  arXiv  Detail & Related papers  (2026-07-21T10:49:29Z)
• A Systematic Post-Train Framework for Video Generation [76.26555417456773]
  Large-scale video diffusion models have demonstrated impressive capabilities in generating high-resolution and semantically rich content.<n>A significant gap remains between their pretraining performance and real-world deployment requirements due to critical issues such as prompt sensitivity, temporal inconsistency, and prohibitive inference costs.<n>We propose a comprehensive post-training framework that systematically aligns pretrained models with user intentions through four synergistic stages.
  arXiv  Detail & Related papers  (2026-04-28T09:34:51Z)
• E2E-Fly: An Integrated Training-to-Deployment System for End-to-End Quadrotor Autonomy [12.44680847653453]
  E2E-Fly is an integrated framework featuring an agile quadrotor platform and a full-stack training, validation, and deployment workflow.<n>We introduce a two-stage validation strategy using sim-to-sim transfer and hardware-in-the-loop testing, and deploy policies onto two physical quadrotor platforms.<n>We demonstrate the effectiveness of our framework for training six end-to-end control tasks and deploy them in the real world.
  arXiv  Detail & Related papers  (2026-04-14T16:00:22Z)
• Enhancing Deep Deterministic Policy Gradients on Continuous Control Tasks with Decoupled Prioritized Experience Replay [3.716862357836751]
  We introduce Decoupled Prioritized Experience Replay (DPER), a novel approach that allows independent sampling of transition batches.<n>DPER can be integrated into any off-policy deep reinforcement learning algorithm that operates in continuous control domains.
  arXiv  Detail & Related papers  (2025-12-04T23:37:29Z)
• A Unified Multi-Task Learning Framework for Generative Auto-Bidding with Validation-Aligned Optimization [51.27959658504722]
  Multi-task learning offers a principled framework to train these tasks jointly through shared representations.<n>Existing multi-task optimization strategies are primarily guided by training dynamics and often generalize poorly in volatile bidding environments.<n>We present Validation-Aligned Multi-task Optimization (VAMO), which adaptively assigns task weights based on the alignment between per-task training gradients and a held-out validation gradient.
  arXiv  Detail & Related papers  (2025-10-09T03:59:51Z)
• CoDiEmb: A Collaborative yet Distinct Framework for Unified Representation Learning in Information Retrieval and Semantic Textual Similarity [20.349897901019574]
  We introduce CoDiEmb, a unified framework for training unified text embeddings.<n>CoDiEmb integrates three key innovations for effective joint optimization.<n>Our results and analysis demonstrate that the framework mitigates cross-task trade-offs.
  arXiv  Detail & Related papers  (2025-08-15T12:46:35Z)
• Feature-Based vs. GAN-Based Learning from Demonstrations: When and Why [50.191655141020505]
  This survey provides a comparative analysis of feature-based and GAN-based approaches to learning from demonstrations.<n>We argue that the dichotomy between feature-based and GAN-based methods is increasingly nuanced.
  arXiv  Detail & Related papers  (2025-07-08T11:45:51Z)
• An End-to-End Reinforcement Learning Based Approach for Micro-View Order-Dispatching in Ride-Hailing [8.892147201091726]
  We propose an end-to-end reinforcement learning based order-dispatching approach in Didi. We employ a two-layer Decision Process framework to model this problem, and present underlineDeep underlineDouble underlineScalable underlineNetwork (DSN2), an encoder-decoder structure network to generate order assignments. By leveraging contextual dynamics, our approach can adapt to the behavioral patterns for better performance.
  arXiv  Detail & Related papers  (2024-08-20T01:30:53Z)
• Exemplar-free Continual Representation Learning via Learnable Drift Compensation [24.114984920918715]
  We propose Learnable Drift Compensation (LDC), which can effectively mitigate drift in any moving backbone. LDC is fast and straightforward to integrate on top of existing continual learning approaches. We achieve state-of-the-art performance in both supervised and semi-supervised settings.
  arXiv  Detail & Related papers  (2024-07-11T14:23:08Z)
• Visual Prompt Tuning in Null Space for Continual Learning [51.96411454304625]
  Existing prompt-tuning methods have demonstrated impressive performances in continual learning (CL) This paper aims to learn each task by tuning the prompts in the direction orthogonal to the subspace spanned by previous tasks' features. In practice, an effective null-space-based approximation solution has been proposed to implement the prompt gradient projection.
  arXiv  Detail & Related papers  (2024-06-09T05:57:40Z)
• Effective Adaptation in Multi-Task Co-Training for Unified Autonomous Driving [103.745551954983]
  In this paper, we investigate the transfer performance of various types of self-supervised methods, including MoCo and SimCLR, on three downstream tasks. We find that their performances are sub-optimal or even lag far behind the single-task baseline. We propose a simple yet effective pretrain-adapt-finetune paradigm for general multi-task training.
  arXiv  Detail & Related papers  (2022-09-19T12:15:31Z)

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.