Linear temporal logic (LTL) is a widely-used task specification language which has a compositional grammar that naturally induces temporally extended behaviours across tasks, including conditionals and alternative realizations. An important problem i RL with LTL tasks is to learn task-conditioned policies which can zero-shot generalize to new LTL instructions not observed in the training. However, because symbolic observation is often lossy and LTL tasks can have long time horizon, previous works can suffer from issues such as training sampling inefficiency and infeasibility or sub-optimality of the found solutions. In order to tackle these issues, this paper proposes a novel multi-task RL algorithm with improved learning efficiency and optimality. To achieve the global optimality of task completion, we propose to learn options dependent on the future subgoals via a novel off-policy approach. In order to propagate the rewards of satisfying future subgoals back more efficiently, we propose to train a multi-step value function conditioned on the subgoal sequence which is updated with Monte Carlo estimates of multi-step discounted returns. In experiments on three different domains, we evaluate the LTL generalization capability of the agent trained by the proposed method, showing its advantage over previous representative methods.
translated by 谷歌翻译
可扩展的网络已经证明了它们在处理灾难性遗忘问题方面的优势。考虑到不同的任务可能需要不同的结构,最近的方法设计了通过复杂技能适应不同任务的动态结构。他们的例程是首先搜索可扩展的结构,然后训练新任务,但是,这将任务分为多个培训阶段,从而导致次优或过度计算成本。在本文中,我们提出了一个名为E2-AEN的端到端可训练的可自适应扩展网络,该网络动态生成了新任务的轻量级结构,而没有任何精确的先前任务下降。具体而言,该网络包含一个功能强大的功能适配器的序列,用于扩大以前学习的表示新任务的表示形式,并避免任务干扰。这些适配器是通过基于自适应门的修剪策略来控制的,该策略决定是否可以修剪扩展的结构,从而根据新任务的复杂性动态地改变网络结构。此外,我们引入了一种新颖的稀疏激活正则化,以鼓励模型学习具有有限参数的区分特征。 E2-aen可以降低成本,并且可以以端到端的方式建立在任何饲喂前架构上。关于分类(即CIFAR和VDD)和检测(即可可,VOC和ICCV2021 SSLAD挑战)的广泛实验证明了提出的方法的有效性,从而实现了新的出色结果。
translated by 谷歌翻译
教深入的强化学习(RL)代理在多任务环境中遵循说明是一个挑战性的问题。我们认为用户通过线性时间逻辑(LTL)公式定义了每个任务。但是,用户可能未知的复杂环境中的某些因果关系依赖性未知。因此,当人类用户指定说明时,机器人无法通过简单地按照给定的说明来解决任务。在这项工作中,我们提出了一个分层增强学习(HRL)框架,其中学习了符号过渡模型,以有效地制定高级计划,以指导代理有效地解决不同的任务。具体而言,符号过渡模型是通过归纳逻辑编程(ILP)学习的,以捕获状态过渡的逻辑规则。通过计划符号过渡模型的乘积和从LTL公式得出的自动机的乘积,代理可以解决因果关系依赖性,并将因果复杂问题分解为一系列简单的低级子任务。我们在离散和连续域中的三个环境上评估了提出的框架,显示了比以前的代表性方法的优势。
translated by 谷歌翻译
在持续学习的SSLAD-TRACK 3B挑战中,我们提出了与变压器(COLT)继续学习的方法。与卷积神经网络相比,我们发现变压器遭受灾难性遗忘的损失。我们方法的主要原则是用旧知识蒸馏和头部扩展策略装备基于变压器的特征提取器来竞争灾难性的遗忘。在本报告中,我们首先介绍了对象检测的持续学习的整体框架。然后,我们分析了解决我们解决方案中灾难性遗址的关键要素对效果。我们的方法在SSLAD-TRACK 3B挑战测试集上实现70.78映射。
translated by 谷歌翻译
为鼓励AI代理商进行有意义的视觉对话(VD),削减了潜力的使用。在钢筋学习中,代表各国至关重要,并根据国家的行动过渡分配奖励。但是,先前的Visual Dialogue Works中的状态表示仅使用文本信息,并且其转换是隐式的。在本文中,我们建议明确关于各国(ECS)代表每轮视觉内容以及在整个视觉对话中关注的内容。 ECS由多模式信息建模,并明确表示。基于ECS,我们制定了两种直观和可意识的奖励,以鼓励视觉对话代理商对多元化和信息的视觉信息相反。根据多种自动指标,人类研究和定性分析,对VideDial V1.0数据集进行了实验结果,使我们的方法能够产生更高的视觉对话代理,以产生更高的视觉对话代理,与以前的方法相比,与以前的方法相比,可以产生更高的视觉相干,更重复和更具视觉信息的对话。
translated by 谷歌翻译
演员 - 评论家RL广泛用于各种机器人控制任务。通过从变分推理(VI)的角度来看演员 - 评论仪RL,训练策略网络以获得给定最优标准的动作的近似。然而,在实践中,演员 - 评论家RL可能会因摊销缺口而产生次优政策估计,并勘探不足。在这项工作中,受到先前使用Hamiltonian Monte Carlo(HMC)在VI中的启发,我们建议将演员 - 评论家RL的政策网络与HMC纳入其中,被称为{\ IT Hamiltonian政策}。因此,我们建议根据HMC从基础政策中发展行动,我们提出的方法具有许多好处。首先,HMC可以改善策略分布,以更好地近似后,因此降低摊销间隙。其次,HMC还可以将勘探更多到具有更高Q值的动作空间区域,提高勘探效率。此外,我们提出了一种新的LEAPFROG运算符来模拟HAMILTONIAN Dynamics。最后,在安全的RL问题中,我们发现所提出的方法不仅可以改善实现的回报,还可以通过丢弃可能的不安全行动来减少安全约束违规行为。在连续控制基线的综合实验实验中,包括Mujoco和Pybullet Roboschool,我们表明该方法是对以前的演员批评方法的数据有效且易于实施的改进。
translated by 谷歌翻译
Text clustering and topic extraction are two important tasks in text mining. Usually, these two tasks are performed separately. For topic extraction to facilitate clustering, we can first project texts into a topic space and then perform a clustering algorithm to obtain clusters. To promote topic extraction by clustering, we can first obtain clusters with a clustering algorithm and then extract cluster-specific topics. However, this naive strategy ignores the fact that text clustering and topic extraction are strongly correlated and follow a chicken-and-egg relationship. Performing them separately fails to make them mutually benefit each other to achieve the best overall performance. In this paper, we propose an unsupervised text clustering and topic extraction framework (ClusTop) which integrates text clustering and topic extraction into a unified framework and can achieve high-quality clustering result and extract topics from each cluster simultaneously. Our framework includes four components: enhanced language model training, dimensionality reduction, clustering and topic extraction, where the enhanced language model can be viewed as a bridge between clustering and topic extraction. On one hand, it provides text embeddings with a strong cluster structure which facilitates effective text clustering; on the other hand, it pays high attention on the topic related words for topic extraction because of its self-attention architecture. Moreover, the training of enhanced language model is unsupervised. Experiments on two datasets demonstrate the effectiveness of our framework and provide benchmarks for different model combinations in this framework.
translated by 谷歌翻译
In this paper, we study the problem of a batch of linearly correlated image alignment, where the observed images are deformed by some unknown domain transformations, and corrupted by additive Gaussian noise and sparse noise simultaneously. By stacking these images as the frontal slices of a third-order tensor, we propose to utilize the tensor factorization method via transformed tensor-tensor product to explore the low-rankness of the underlying tensor, which is factorized into the product of two smaller tensors via transformed tensor-tensor product under any unitary transformation. The main advantage of transformed tensor-tensor product is that its computational complexity is lower compared with the existing literature based on transformed tensor nuclear norm. Moreover, the tensor $\ell_p$ $(0<p<1)$ norm is employed to characterize the sparsity of sparse noise and the tensor Frobenius norm is adopted to model additive Gaussian noise. A generalized Gauss-Newton algorithm is designed to solve the resulting model by linearizing the domain transformations and a proximal Gauss-Seidel algorithm is developed to solve the corresponding subproblem. Furthermore, the convergence of the proximal Gauss-Seidel algorithm is established, whose convergence rate is also analyzed based on the Kurdyka-$\L$ojasiewicz property. Extensive numerical experiments on real-world image datasets are carried out to demonstrate the superior performance of the proposed method as compared to several state-of-the-art methods in both accuracy and computational time.
translated by 谷歌翻译
深层剩余网络(RESNET)在各种现实世界应用中显示出最先进的性能。最近,重新聚集了重新分解模型并将其解释为连续的普通微分方程或神经模型的解决方案。在这项研究中,我们提出了一个具有层变化参数的神经通用的普通微分方程(神经 - 理)模型,以进一步扩展神经模块以近似离散的重新NET。具体而言,我们使用非参数B-Spline函数来参数化神经形成,以便可以轻松平衡模型复杂性和计算效率之间的权衡。证明重新结构和神经码模型是所提出的神经形模型的特殊情况。基于两个基准数据集,MNIST和CIFAR-10,我们表明,与标准神经模板相比,与层变化的神经形成更加灵活和通用。此外,神经学享有计算和记忆益处,同时在预测准确性方面具有相当的性能。
translated by 谷歌翻译
机器学习辅助建模的原子势能表面(PES)正在彻底改变分子模拟的领域。随着高质量电子结构数据的积累,可以在所有可用数据上鉴定的模型,并在下游任务上以较小的额外努力进行填充,这将使该领域进入新阶段。在这里,我们提出了DPA-1,这是一种具有新颖的注意机制的深层潜在模型,该模型非常有效地表示原子系统的构象和化学空间并学习PES。我们在许多系统上测试了DPA-1,并且与现有基准相比,观察到了卓越的性能。当在包含56个元素的大规模数据集上进行预估计时,DPA-1可以成功应用于各种下游任务,并有很大的提高样品效率。令人惊讶的是,对于不同的元素,学习的类型嵌入参数在潜在空间中形成$螺旋$,并具有自然对应的元素性表位,显示了预审预周化的DPA-1模型的有趣解释性。
translated by 谷歌翻译