Curriculum-Based Iterative Self-Play for Scalable Multi-Drone Racing

• URL: http://arxiv.org/abs/2510.22570v1
• Date: Sun, 26 Oct 2025 08:03:06 GMT
• Title: Curriculum-Based Iterative Self-Play for Scalable Multi-Drone Racing
• Abstract summary: CRUISE is a reinforcement learning framework for multi-drone racing.<n>It combines a progressive difficulty curriculum with an efficient self-play mechanism to foster robust competitive behaviors.<n>It achieves nearly double the planner's mean racing speed, maintains high success rates, and demonstrates robust scalability as agent density increases.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: The coordination of multiple autonomous agents in high-speed, competitive environments represents a significant engineering challenge. This paper presents CRUISE (Curriculum-Based Iterative Self-Play for Scalable Multi-Drone Racing), a reinforcement learning framework designed to solve this challenge in the demanding domain of multi-drone racing. CRUISE overcomes key scalability limitations by synergistically combining a progressive difficulty curriculum with an efficient self-play mechanism to foster robust competitive behaviors. Validated in high-fidelity simulation with realistic quadrotor dynamics, the resulting policies significantly outperform both a standard reinforcement learning baseline and a state-of-the-art game-theoretic planner. CRUISE achieves nearly double the planner's mean racing speed, maintains high success rates, and demonstrates robust scalability as agent density increases. Ablation studies confirm that the curriculum structure is the critical component for this performance leap. By providing a scalable and effective training methodology, CRUISE advances the development of autonomous systems for dynamic, competitive tasks and serves as a blueprint for future real-world deployment.

Related papers

• Dual Process Motion Planning [53.570848178455776]
  We introduce a dual-process architecture that combines the strengths of robust reasoning and learning.<n>Our framework integrates state-of-the-art symbolic solvers as a System-2'' component with experience-driven System-1'' modules.
  arXiv  Detail & Related papers  (2026-09-01T13:52:12Z)
• Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills [53.15216425100295]
  We introduce Skill Self-Play (Skill-SP), a co-evolutionary framework comprising a proposer, a solver, and a skill controller.<n>The proposer generates challenging tasks conditioned on dynamically sampled skills; the solver explores candidate solutions to push its capability boundaries; and the skill controller collects execution feedback to update and expand the skill library.<n>This interactive co-evolution effectively bridges the gap between structured verification and open-ended exploration.
  arXiv  Detail & Related papers  (2026-07-24T17:59:22Z)
• World Models as Adversaries: Multi-Agent Self-Play Fine-Tuning for Robust Motion Planning [60.88859946006306]
  Adversa World Modeling is a theoretically grounded multi-agent self-play fine-tuning framework.<n>In inner minimization, the planner's predictive world model is converted into a role-conditioned adversary that learns sparse, scene-adaptive attack coalitions.<n> Experiments on the nuPlan and InterPlan benchmarks demonstrate that our method generates transferable adversarial interactions.
  arXiv  Detail & Related papers  (2026-07-12T07:44:16Z)
• Self-Paced Curriculum Reinforcement Learning for Autonomous Superbike Racing in Simulation [9.439483772106346]
  We present a framework for training an autonomous agent to race a superbike in VRider SBK, a physics-accurate Unity-based motorbike simulator.<n>Preliminary results demonstrate that SPDL outperforms SAC alone in training efficiency, lap time, and driving stability across multiple tracks and motorbike models.
  arXiv  Detail & Related papers  (2026-06-08T09:14:12Z)
• MAPLE: Latent Multi-Agent Play for End-to-End Autonomous Driving [62.43744546817599]
  Vision-language--action (VLA) models are effective as end-to-end motion planners, but can be brittle when evaluated in closed-loop settings.<n>We propose MAPLE, a novel framework for reactive, multi-agent rollout of a dynamic driving scenario in the latent space of the VLA model.<n> MAPLE achieves state-of-the-art driving performance on Bench2Drive and demonstrates scalable, closed-loop multi-agent play for robust E2E autonomous driving systems.
  arXiv  Detail & Related papers  (2026-05-13T23:35:14Z)
• Learning Reactive Dexterous Grasping via Hierarchical Task-Space RL Planning and Joint-Space QP Control [50.28263951510334]
  We propose a hybrid hierarchical control framework for reactive dexterous grasping.<n>The proposed framework explicitly decouples high-level spatial intent from low-level joint execution.<n>We extensively validate the proposed framework through a rigorous simulation-to-reality pipeline.
  arXiv  Detail & Related papers  (2026-05-05T04:49:38Z)
• MAVEN-T: Multi-Agent enVironment-aware Enhanced Neural Trajectory predictor with Reinforcement Learning [0.0]
  MAVEN-T is a teacher-student framework that achieves state-of-the-art trajectory prediction.<n>The framework incorporates reinforcement learning to overcome the imitation ceiling of traditional distillation.<n>Experiments on NGSIM and highD datasets demonstrate 6.2x parameter compression and 3.7x inference speedup.
  arXiv  Detail & Related papers  (2026-04-11T11:34:13Z)
• Actor-Curator: Co-adaptive Curriculum Learning via Policy-Improvement Bandits for RL Post-Training [63.34044358216334]
  ACTOR-CURATOR is a scalable and fully automated curriculum learning framework for reinforcement learning post-training of large language models.<n> Empirically, ACTOR-CURATOR consistently outperforms uniform sampling and strong curriculum baselines.
  arXiv  Detail & Related papers  (2026-02-24T04:19:48Z)
• LongCat-Flash-Thinking-2601 Technical Report [134.89732115690705]
  LongCat-Flash-Thinking-2601 is an open-source Mixture-of-Experts (MoE) reasoning model with superior agentic reasoning capability.<n>LongCat-Flash-Thinking-2601 achieves state-of-the-art performance among open-source models on a wide range of agentic benchmarks.
  arXiv  Detail & Related papers  (2026-01-23T13:20:09Z)
• FASTer: Toward Efficient Autoregressive Vision Language Action Modeling via Neural Action Tokenization [61.10456021136654]
  We introduce FASTer, a unified framework for efficient and general robot learning.<n>FASTerVQ encodes action chunks as single-channel images, capturing global-temporal dependencies while maintaining a high compression ratio.<n>FASTerVLA builds on this tokenizer with block-wise autoregressive decoding and a lightweight action expert, achieving both faster inference and higher task performance.
  arXiv  Detail & Related papers  (2025-12-04T16:21:38Z)
• DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Models [51.76664843721462]
  DeepThinkVLA is a new architecture for Vision-Language-Action models.<n>It generates sequential CoT with causal attention and switches to bidirectional attention for fast decoding of action vectors.<n>It achieves a 97.0% success rate on the LIBERO benchmark.
  arXiv  Detail & Related papers  (2025-10-31T05:26:16Z)
• SPIRAL: Self-Play Incremental Racing Algorithm for Learning in Multi-Drone Competitions [0.0]
  This paper introduces SPIRAL, a novel approach for training autonomous drones in multi-agent racing competitions.<n> SPIRAL distinctively employs a self-play mechanism to incrementally cultivate complex racing behaviors.<n>Our method is designed for versatility, allowing integration with any state-of-the-art Deep Reinforcement Learning (DRL) algorithms.
  arXiv  Detail & Related papers  (2025-10-26T07:59:44Z)
• Curriculum Learning With Counterfactual Group Relative Policy Advantage For Multi-Agent Reinforcement Learning [15.539607264374242]
  Multi-agent reinforcement learning (MARL) has achieved strong performance in cooperative adversarial tasks.<n>We propose a dynamic curriculum learning framework that employs an self-adaptive difficulty adjustment mechanism.<n>Our method improves both training stability and final performance, achieving competitive results against state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-06-09T08:38:18Z)
• Digital Twin Synchronization: Bridging the Sim-RL Agent to a Real-Time Robotic Additive Manufacturing Control [2.5709786140685633]
  This research advances the integration of Soft Actor-Critic with digital twins for industrial robotics applications.<n>The system architecture combines Unity's simulation environment with ROS2 for seamless digital twin synchronization.<n>Results show rapid policy convergence and robust task execution in both simulated and physical environments.
  arXiv  Detail & Related papers  (2025-01-29T22:06:53Z)
• Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Robotics [50.191655141020505]
  This work advances model-based reinforcement learning by addressing the challenges of long-horizon prediction, error accumulation, and sim-to-real transfer.<n>By providing a scalable and robust framework, the introduced methods pave the way for adaptive and efficient robotic systems in real-world applications.
  arXiv  Detail & Related papers  (2025-01-17T10:39:09Z)
• LoRA-IR: Taming Low-Rank Experts for Efficient All-in-One Image Restoration [62.3751291442432]
  We propose LoRA-IR, a flexible framework that dynamically leverages compact low-rank experts to facilitate efficient all-in-one image restoration. LoRA-IR consists of two training stages: degradation-guided pre-training and parameter-efficient fine-tuning. Experiments demonstrate that LoRA-IR achieves SOTA performance across 14 IR tasks and 29 benchmarks, while maintaining computational efficiency.
  arXiv  Detail & Related papers  (2024-10-20T13:00:24Z)
• Scalable Supervisory Architecture for Autonomous Race Cars [0.0]
  This paper presents a scalable architecture designed for autonomous racing. It emphasizes modularity, adaptability to diverse configurations, and the ability to supervise parallel execution of pipelines. The results confirm the architecture's scalability and versatility, providing a robust foundation for the development of competitive autonomous racing systems.
  arXiv  Detail & Related papers  (2024-08-27T13:19:17Z)
• An Imitative Reinforcement Learning Framework for Pursuit-Lock-Launch Missions [9.002353110876529]
  Unmanned Combat Aerial Vehicle (UCAV) Within-Visual-Range (WVR) engagement plays a decisive role on the aerial battlefields.<n>We propose a novel imitative reinforcement learning framework, which efficiently leverages expert data while enabling autonomous exploration.<n>Our framework can quickly learn the critical knowledge in complex aerial combat tasks, achieving up to a 100% success rate and demonstrating excellent robustness.
  arXiv  Detail & Related papers  (2024-06-17T13:59:52Z)
• RILe: Reinforced Imitation Learning [60.63173816209543]
  RILe (Reinforced Learning) is a framework that combines the strengths of imitation learning and inverse reinforcement learning to learn a dense reward function efficiently.<n>Our framework produces high-performing policies in high-dimensional tasks where direct imitation fails to replicate complex behaviors.
  arXiv  Detail & Related papers  (2024-06-12T17:56:31Z)
• Aquatic Navigation: A Challenging Benchmark for Deep Reinforcement Learning [53.3760591018817]
  We propose a new benchmarking environment for aquatic navigation using recent advances in the integration between game engines and Deep Reinforcement Learning. Specifically, we focus on PPO, one of the most widely accepted algorithms, and we propose advanced training techniques. Our empirical evaluation shows that a well-designed combination of these ingredients can achieve promising results.
  arXiv  Detail & Related papers  (2024-05-30T23:20:23Z)
• When Does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning? [99.4914671654374]
  We propose AdvCL, a novel adversarial contrastive pretraining framework. We show that AdvCL is able to enhance cross-task robustness transferability without loss of model accuracy and finetuning efficiency.
  arXiv  Detail & Related papers  (2021-11-01T17:59:43Z)

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.