做无人机导航或机器人强化学习的团队，终于有了能自动设计奖励函数并自我优化的框架，省去大量手动调参时间，建议直接看实验部分。
AgenticRL 是一种结合多模态 GPT 智能体的强化学习框架，专为无人机视觉导航任务设计。它通过 GPT 智能体自动生成奖励函数、训练策略并自我评估，形成闭环自优化流程。在多种导航任务（如穿越门、避障、轨迹跟踪）中，闭环优化使策略性能提升71%。该框架还支持从仿真到真实环境的迁移，真实世界成功率达91%，仿真到真实准确率94%。这大幅减少了传统强化学习中对人工设计奖励和反复调参的依赖。
Self-Refining Agentic Reinforcement Learning for Vision-Conditioned UAV Navigation
Deep reinforcement learning has shown strong potential for enabling autonomous robots to learn complex navigational tasks. However, its practical use still depends heavily on human designed reward functions and repeated manual fine tuning, which is time consuming and does not guarantee high success in the desired task. This paper presents AgenticRL, agent guided reinforcement learning framework that increases autonomy in reward design, policy refinement, and real world deployment for unmanned aerial vehicles (UAV) navigation tasks. AgenticRL uses a multimodal generative pre-trained tansformer (GPT) agent to interpret task information and visual scene observations, generate task specific reward functions, train policies using Proximal Policy Optimization (PPO) algorithm, and then act as a critic by evaluating the trained policy through diagnosis packets to generate feedback. Based on this feedback, the agent identifies failure modes and refines the reward function in a closed loop self improvement process. To further leverage the multimodal GPT agent during inference, AgenticRL uses real world images and natural language task information to automatically identify the active scenario and select the appropriate trained policy for execution. The framework is evaluated on multiple navigational tasks, including gate traversal, obstacle avoidance, wall barrier crossing with landing, trajectory following, and motion behavior learning. Experimental results show that the closed loop refinement process improves policy behavior compared with initial rewards by 71%. We also demonstrate sim-to-real transfer of the proposed framework, achieving a real world success rate of 91% and a sim-to-real accuracy of 94%.