发表机构
Rutgers University–New Brunswick; Politecnico di Milano（罗格斯大学新布朗斯维克分校; 米兰理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出GenAIF框架，利用生成式轨迹模型从演示中学习以实现主动推断控制，并通过基准测试证明扩散模型控制性能最佳，CVAE推理更快，且共享模型可连接动作提议、预测与观测证据。
AI 中文摘要
从轨迹演示中学习为主动推断控制复杂系统提供了一条途径，这类系统的动力学难以显式建模。我们引入了生成式主动推断控制（GenAIF），其中一个生成式轨迹模型从演示和测量的动作干预中学习，以提供目标条件策略分布和状态到观测的似然映射。基于这一控制设计，我们推导出三个模型要求：（i）有用的动作提议，（ii）在施加动作下的准确预测，以及（iii）用于信念更新和预期信息增益的概率性观测证据。我们在具有多种物理条件的MuJoCo操作任务中对扩散模型、自回归Transformer、条件变分自编码器（CVAE）和流匹配进行了基准测试。扩散模型在测试的动力学中提供了最强的控制，而CVAE在相当短视界预测的同时实现了更快的推理。正确的条件设置是决定性的，轨迹重用进一步节省了计算成本。使用相同的冻结模型，一个隐藏动力学实验展示了在未宣布的倾斜变化后提示信念适应；随后的不稳定性表明持续推理仍然是一个挑战。这些发现支持使用共享的生成式轨迹模型来连接动作提议、受控预测和观测证据，从而在GenAIF中实现统一。
英文摘要
Learning from trajectory demonstrations offers a route to active-inference control of complex systems whose dynamics are difficult to model explicitly. We introduce generative active-inference control (GenAIF), in which one generative trajectory model learns from demonstrations and measured action interventions to supply a goal-conditioned policy distribution and a state-to-observation likelihood mapping. From this control design, we derive three model requirements: (i) useful action proposals, (ii) accurate prediction under imposed actions, and (iii) probabilistic observation evidence for belief updating and expected information gain. We benchmark diffusion, autoregressive Transformers, conditional variational autoencoders (CVAEs), and flow matching in a MuJoCo manipulation task with multiple physical conditions. Diffusion delivers the strongest control across the tested dynamics, while CVAE combines comparable short-horizon prediction with much faster inference. Correct conditioning is decisive, and trajectory reuse offers further computational savings. In replay after an unannounced tilt change, pretrained diffusion updates belief fastest among the original models; fine-tuning on recovery demonstrations further accelerates identification and sustains accurate tracking. These findings support the use of shared generative trajectory models to connect action proposal, controlled prediction, and observation evidence within GenAIF.
CommentsAccepted at the 7th International Workshop on Active Inference (IWAI 2026). Code: https://github.com/lyeeonardo/generative-trajectory-benchmark
