Communication enables agents to cooperate to achieve their goals. Learning when to communicate, i.e., sparse (in time) communication, and whom to message is particularly important when bandwidth is limited. Recent work in learning sparse individualized communication, however, suffers from high variance during training, where decreasing communication comes at the cost of decreased reward, particularly in cooperative tasks. We use the information bottleneck to reframe sparsity as a representation learning problem, which we show naturally enables lossless sparse communication at lower budgets than prior art. In this paper, we propose a method for true lossless sparsity in communication via Information Maximizing Gated Sparse Multi-Agent Communication (IMGS-MAC). Our model uses two individualized regularization objectives, an information maximization autoencoder and sparse communication loss, to create informative and sparse communication. We evaluate the learned communication `language' through direct causal analysis of messages in non-sparse runs to determine the range of lossless sparse budgets, which allow zero-shot sparsity, and the range of sparse budgets that will inquire a reward loss, which is minimized by our learned gating function with few-shot sparsity. To demonstrate the efficacy of our results, we experiment in cooperative multi-agent tasks where communication is essential for success. We evaluate our model with both continuous and discrete messages. We focus our analysis on a variety of ablations to show the effect of message representations, including their properties, and lossless performance of our model.

新兴的沟通研究通常着重于优化特定于任务的效用作为沟通的驱动力。但是，通过优化信息和复杂性之间的信息瓶颈权衡，人类语言似乎在压力下发展，以有效地将含义压缩到通信信号中。在这项工作中，我们研究了如何交换这三个因素 - 效用，信息性和复杂性 - 与人类交流相比，包括新兴的沟通。为此，我们提出了矢量定量的变分信息瓶颈（VQ-VIB），这是一种训练神经剂将输入压缩到嵌入连续空间中的离散信号的方法。我们通过VQ-VIB训练代理商，并将其性能与以前建议的神经体系结构在接地环境和刘易斯参考游戏中进行比较。在所有神经体系结构和环境中，考虑到沟通信息有益的沟通融合率，并惩罚交流复杂性会导致类似人类的词典大小，同时保持高效用。此外，我们发现VQ-VIB优于其他离散通信方法。这项工作表明，人们认为人类语言进化的基本原理如何为人工代理中的新兴沟通提供信息。

在强化学习培训的设置代理神经学可以通过分立令牌相互通信，实现作为一个团队有哪些代理将无法独自做到。然而，使用一个热向量作为离散的通信的当前标准从获取作为零次理解通信这样的更理想的方面令牌防止剂。通过嵌入一词从自然语言处理技术的启发，我们提出了神经代理架构，使他们能够通过从了解到，连续的空间衍生离散令牌进行通信。我们显示了在决策理论框架，我们的技术优化通信在大范围的场景，而一个热令牌是唯一最佳的下严格的假设。在自我发挥的实验，我们验证了我们的培训的工作人员学习集群令牌语义有意义的方式，让他们在其他技术无法嘈杂的环境中交流。最后，我们证明这两种，用我们的方法代理可以有效地应对新的人际交往和人类可以理解未标记的应急代理通信，跑赢使用一个热的沟通。

Imitation learning (IL) is a simple and powerful way to use high-quality human driving data, which can be collected at scale, to identify driving preferences and produce human-like behavior. However, policies based on imitation learning alone often fail to sufficiently account for safety and reliability concerns. In this paper, we show how imitation learning combined with reinforcement learning using simple rewards can substantially improve the safety and reliability of driving policies over those learned from imitation alone. In particular, we use a combination of imitation and reinforcement learning to train a policy on over 100k miles of urban driving data, and measure its effectiveness in test scenarios grouped by different levels of collision risk. To our knowledge, this is the first application of a combined imitation and reinforcement learning approach in autonomous driving that utilizes large amounts of real-world human driving data.

Reliably planning fingertip grasps for multi-fingered hands lies as a key challenge for many tasks including tool use, insertion, and dexterous in-hand manipulation. This task becomes even more difficult when the robot lacks an accurate model of the object to be grasped. Tactile sensing offers a promising approach to account for uncertainties in object shape. However, current robotic hands tend to lack full tactile coverage. As such, a problem arises of how to plan and execute grasps for multi-fingered hands such that contact is made with the area covered by the tactile sensors. To address this issue, we propose an approach to grasp planning that explicitly reasons about where the fingertips should contact the estimated object surface while maximizing the probability of grasp success. Key to our method's success is the use of visual surface estimation for initial planning to encode the contact constraint. The robot then executes this plan using a tactile-feedback controller that enables the robot to adapt to online estimates of the object's surface to correct for errors in the initial plan. Importantly, the robot never explicitly integrates object pose or surface estimates between visual and tactile sensing, instead it uses the two modalities in complementary ways. Vision guides the robots motion prior to contact; touch updates the plan when contact occurs differently than predicted from vision. We show that our method successfully synthesises and executes precision grasps for previously unseen objects using surface estimates from a single camera view. Further, our approach outperforms a state of the art multi-fingered grasp planner, while also beating several baselines we propose.

Hawkes processes have recently risen to the forefront of tools when it comes to modeling and generating sequential events data. Multidimensional Hawkes processes model both the self and cross-excitation between different types of events and have been applied successfully in various domain such as finance, epidemiology and personalized recommendations, among others. In this work we present an adaptation of the Frank-Wolfe algorithm for learning multidimensional Hawkes processes. Experimental results show that our approach has better or on par accuracy in terms of parameter estimation than other first order methods, while enjoying a significantly faster runtime.

Importance: Social determinants of health (SDOH) are known to be associated with increased risk of suicidal behaviors, but few studies utilized SDOH from unstructured electronic health record (EHR) notes. Objective: To investigate associations between suicide and recent SDOH, identified using structured and unstructured data. Design: Nested case-control study. Setting: EHR data from the US Veterans Health Administration (VHA). Participants: 6,122,785 Veterans who received care in the US VHA between October 1, 2010, and September 30, 2015. Exposures: Occurrence of SDOH over a maximum span of two years compared with no occurrence of SDOH. Main Outcomes and Measures: Cases of suicide deaths were matched with 4 controls on birth year, cohort entry date, sex, and duration of follow-up. We developed an NLP system to extract SDOH from unstructured notes. Structured data, NLP on unstructured data, and combining them yielded seven, eight and nine SDOH respectively. Adjusted odds ratios (aORs) and 95% confidence intervals (CIs) were estimated using conditional logistic regression. Results: In our cohort, 8,821 Veterans committed suicide during 23,725,382 person-years of follow-up (incidence rate 37.18 /100,000 person-years). Our cohort was mostly male (92.23%) and white (76.99%). Across the six common SDOH as covariates, NLP-extracted SDOH, on average, covered 84.38% of all SDOH occurrences. All SDOH, measured by structured data and NLP, were significantly associated with increased risk of suicide. The SDOH with the largest effects was legal problems (aOR=2.67, 95% CI=2.46-2.89), followed by violence (aOR=2.26, 95% CI=2.11-2.43). NLP-extracted and structured SDOH were also associated with suicide. Conclusions and Relevance: NLP-extracted SDOH were always significantly associated with increased risk of suicide among Veterans, suggesting the potential of NLP in public health studies.

Multilevel Stein variational gradient descent is a method for particle-based variational inference that leverages hierarchies of approximations of target distributions with varying costs and fidelity to computationally speed up inference. This work provides a cost complexity analysis of multilevel Stein variational gradient descent that applies under milder conditions than previous results, especially in discrete-in-time regimes and beyond the limited settings where Stein variational gradient descent achieves exponentially fast convergence. The analysis shows that the convergence rate of Stein variational gradient descent enters only as a constant factor for the cost complexity of the multilevel version, which means that the costs of the multilevel version scale independently of the convergence rate of Stein variational gradient descent on a single level. Numerical experiments with Bayesian inverse problems of inferring discretized basal sliding coefficient fields of the Arolla glacier ice demonstrate that multilevel Stein variational gradient descent achieves orders of magnitude speedups compared to its single-level version.

Long short-term memory (LSTM) is a type of powerful deep neural network that has been widely used in many sequence analysis and modeling applications. However, the large model size problem of LSTM networks make their practical deployment still very challenging, especially for the video recognition tasks that require high-dimensional input data. Aiming to overcome this limitation and fully unlock the potentials of LSTM models, in this paper we propose to perform algorithm and hardware co-design towards high-performance energy-efficient LSTM networks. At algorithm level, we propose to develop fully decomposed hierarchical Tucker (FDHT) structure-based LSTM, namely FDHT-LSTM, which enjoys ultra-low model complexity while still achieving high accuracy. In order to fully reap such attractive algorithmic benefit, we further develop the corresponding customized hardware architecture to support the efficient execution of the proposed FDHT-LSTM model. With the delicate design of memory access scheme, the complicated matrix transformation can be efficiently supported by the underlying hardware without any access conflict in an on-the-fly way. Our evaluation results show that both the proposed ultra-compact FDHT-LSTM models and the corresponding hardware accelerator achieve very high performance. Compared with the state-of-the-art compressed LSTM models, FDHT-LSTM enjoys both order-of-magnitude reduction in model size and significant accuracy improvement across different video recognition datasets. Meanwhile, compared with the state-of-the-art tensor decomposed model-oriented hardware TIE, our proposed FDHT-LSTM architecture achieves better performance in throughput, area efficiency and energy efficiency, respectively on LSTM-Youtube workload. For LSTM-UCF workload, our proposed design also outperforms TIE with higher throughput, higher energy efficiency and comparable area efficiency.

The potential of offline reinforcement learning (RL) is that high-capacity models trained on large, heterogeneous datasets can lead to agents that generalize broadly, analogously to similar advances in vision and NLP. However, recent works argue that offline RL methods encounter unique challenges to scaling up model capacity. Drawing on the learnings from these works, we re-examine previous design choices and find that with appropriate choices: ResNets, cross-entropy based distributional backups, and feature normalization, offline Q-learning algorithms exhibit strong performance that scales with model capacity. Using multi-task Atari as a testbed for scaling and generalization, we train a single policy on 40 games with near-human performance using up-to 80 million parameter networks, finding that model performance scales favorably with capacity. In contrast to prior work, we extrapolate beyond dataset performance even when trained entirely on a large (400M transitions) but highly suboptimal dataset (51% human-level performance). Compared to return-conditioned supervised approaches, offline Q-learning scales similarly with model capacity and has better performance, especially when the dataset is suboptimal. Finally, we show that offline Q-learning with a diverse dataset is sufficient to learn powerful representations that facilitate rapid transfer to novel games and fast online learning on new variations of a training game, improving over existing state-of-the-art representation learning approaches.