Motion planning is the soul of robot decision making. Classical planning
algorithms like graph search and reaction-based algorithms face challenges in
cases of dense and dynamic obstacles. Deep learning algorithms generate
suboptimal one-step predictions that cause many collisions. Reinforcement
learning algorithms generate optimal or near-optimal time-sequential
predictions. However, they suffer from slow convergence, suboptimal converged
results, and overfittings. This paper introduces a hybrid algorithm for robotic
motion planning: long short-term memory (LSTM) pooling and skip connection for
attention-based discrete soft actor critic (LSA-DSAC). First, graph network
(relational graph) and attention network (attention weight) interpret the
environmental state for the learning of the discrete soft actor critic
algorithm. The expressive power of attention network outperforms that of graph
in our task by difference analysis of these two representation methods.
However, attention based DSAC faces the overfitting problem in training.
Second, the skip connection method is integrated to attention based DSAC to
mitigate overfitting and improve convergence speed. Third, LSTM pooling is
taken to replace the sum operator of attention weigh and eliminate overfitting
by slightly sacrificing convergence speed at early-stage training. Experiments
show that LSA-DSAC outperforms the state-of-the-art in training and most
evaluations. The physical robot is also implemented and tested in the real
world.

混合算法 LSTM 池化和跳跃连接的注意力型离散软演员评论家 (LSA-DSAC) 用于机器人运动规划，取代了基于图的算法并改善了收敛速度。实验证明 LSA-DSAC 在训练和评估中优于最先进的方法，并在实际世界中实施和测试了物理机器人。

表示学习与强化学习的混合在动态复杂机器人运动规划中的应用

Hybrid of representation learning and reinforcement learning for dynamic  and complex robotic motion planning

Hierarchical multi-label academic text classification (HMTC) is to assign
academic texts into a hierarchically structured labeling system. We propose an
attention-based hierarchical multi-label classification algorithm of academic
texts (AHMCA) by integrating features such as text, keywords, and hierarchical
structure, the academic documents are classified into the most relevant
categories. We utilize word2vec and BiLSTM to obtain embedding and latent
vector representations of text, keywords, and hierarchies. We use hierarchical
attention mechanism to capture the associations between keywords, label
hierarchies, and text word vectors to generate hierarchical-specific document
embedding vectors to replace the original text embeddings in HMCN-F. The
experimental results on the academic text dataset demonstrate the effectiveness
of the AHMCA algorithm.

本文提出了一种基于注意力机制的层次化多标签学术文本分类算法，该算法结合了文本、关键词和层次结构等特征，利用 word2vec 和 BiLSTM 来获取文本、关键词和层次结构的嵌入式和潜在向量表示，并使用分层注意机制来捕捉关键词、标签层次结构和文本词向量之间的关联，以生成特定于分层的文档嵌入向量取代 HMCN-F 中的原始文本嵌入。实验结果显示，该算法具有较好的效果。

基于注意力的学术资源文本级多标签分类

Academic Resource Text Level Multi-label Classification based on Attention

This paper presents a novel attention-based algorithm for achieving adaptive
computation called DACT, which, unlike existing ones, is end-to-end
differentiable. Our method can be used in conjunction with many networks; in
particular, we study its application to the widely known MAC architecture,
obtaining a significant reduction in the number of recurrent steps needed to
achieve similar accuracies, therefore improving its performance to computation
ratio. Furthermore, we show that by increasing the maximum number of steps
used, we surpass the accuracy of even our best non-adaptive MAC in the CLEVR
dataset, demonstrating that our approach is able to control the number of steps
without significant loss of performance. Additional advantages provided by our
approach include considerably improving interpretability by discarding useless
steps and providing more insights into the underlying reasoning process.
Finally, we present adaptive computation as an equivalent to an ensemble of
models, similar to a mixture of expert formulation. Both the code and the
configuration files for our experiments are made available to support further
research in this area.

本文介绍了一种新颖的基于注意力机制的自适应计算算法，称为 DACT，与现有算法不同，是端到端可微的。该算法可以与许多网络配合使用；特别地，我们研究了其在广泛使用的 MAC 体系结构中的应用，使所需的循环步骤数量显著减少，从而改善了其性能与计算比率。此外，我们还表明，通过增加所使用的最大步骤数，即使在 CLEVR 数据集中也能超越我们最佳的非自适应 MAC 的准确性，证明我们的方法能够控制步骤数而不会显著降低性能。我们的方法提供的额外优点包括通过丢弃无用的步骤，并提供对底层推理过程的更多见解，从而显着提高了可解释性。最后，我们将自适应计算呈现为模型集成的等价形式，类似于专家混合配方。我们的实验代码和配置文件均可用于支持这一领域的进一步研究。