用超网络生成任务专属策略参数，提升机器人操作在多变环境中的适应性。
Hyper-GoalNet: Goal-Conditioned Manipulation Policy Learning with HyperNetworks
- 通过超网络将目标信息转化为策略网络参数，分离目标理解与状态处理。
- 在复杂环境下比现有方法提升显著，尤其在高变化条件下性能更优。
- 适合研究机器人强化学习、目标条件策略的开发者或工程师参考。
面向机器人操作的目标条件策略学习面临在多样目标任务与环境中保持性能的挑战。本文提出 Hyper-GoalNet 框架，利用超网络根据目标规范生成特定任务的策略网络参数。与传统方法仅将固定网络条件化于目标状态对不同，本方法将目标解析与状态处理解耦：前者决定网络参数，后者应用这些参数处理当前观测。为提升表征质量以实现有效策略生成，我们在潜在空间中引入两项互补约束：(1) 前向动力学模型，增强状态转移的可预测性；(2) 距离约束，确保向目标状态单调逼近。我们在包含多种环境随机化的操作任务上评估该方法，结果表明其在多种场景下均显著优于当前最优方法，尤其在高变异条件下表现突出。真实机器人实验进一步验证了该方法对传感器噪声和物理不确定性的鲁棒性。代码已开源：https://github.com/wantingyao/hyper-goalnet。
原文摘要 · Abstract (English)
Goal-conditioned policy learning for robotic manipulation presents significant challenges in maintaining performance across diverse objectives and environments. We introduce Hyper-GoalNet, a framework that generates task-specific policy network parameters from goal specifications using hypernetworks. Unlike conventional methods that simply condition fixed networks on goal-state pairs, our approach separates goal interpretation from state processing -- the former determines network parameters while the latter applies these parameters to current observations. To enhance representation quality for effective policy generation, we implement two complementary constraints on the latent space: (1) a forward dynamics model that promotes state transition predictability, and (2) a distance-based constraint ensuring monotonic progression toward goal states. We evaluate our method on a comprehensive suite of manipulation tasks with varying environmental randomization. Results demonstrate significant performance improvements over state-of-the-art methods, particularly in high-variability conditions. Real-world robotic experiments further validate our method's robustness to sensor noise and physical uncertainties. Code is available at: https://github.com/wantingyao/hyper-goalnet.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。