深度神经网络是当今离线增强学习中最常用的功能近似值。先前的工作表明，接受TD学习和梯度下降训练的神经网可以表现出隐式正则化，可以通过这些网络的参数化不足来表征。具体而言，已经观察到在训练期间，倒数第二个特征层的排名（也称为\ textit {有效等级}）急剧崩溃。反过来，这种崩溃被认为是为了降低模型在学习后期进一步适应的能力，从而导致最终表现降低。有效等级和绩效之间的这种关联使离线RL的有效等级引人注目，主要用于离线政策评估。在这项工作中，我们对三个离线RL数据集的有效等级与绩效之间的关系进行了仔细的实证研究：Bsuite，Atari和DeepMind Lab。我们观察到，直接关联仅存在于受限的设置中，并且在更广泛的超参数扫描中消失。此外，我们从经验上确定了三个学习的阶段，这些阶段解释了隐式正则化对学习动力学的影响，并发现单独进行引导不足以解释有效等级的崩溃。此外，我们表明其他几个因素可能会混淆有效的等级与绩效之间的关系，并得出结论，在简单假设下研究这种关联可能会产生高度误导。

深度强化学习（RL）导致了许多最近和开创性的进步。但是，这些进步通常以培训的基础体系结构的规模增加以及用于训练它们的RL算法的复杂性提高，而均以增加规模的成本。这些增长反过来又使研究人员更难迅速原型新想法或复制已发表的RL算法。为了解决这些问题，这项工作描述了ACME，这是一个用于构建新型RL算法的框架，这些框架是专门设计的，用于启用使用简单的模块化组件构建的代理，这些组件可以在各种执行范围内使用。尽管ACME的主要目标是为算法开发提供一个框架，但第二个目标是提供重要或最先进算法的简单参考实现。这些实现既是对我们的设计决策的验证，也是对RL研究中可重复性的重要贡献。在这项工作中，我们描述了ACME内部做出的主要设计决策，并提供了有关如何使用其组件来实施各种算法的进一步详细信息。我们的实验为许多常见和最先进的算法提供了基准，并显示了如何为更大且更复杂的环境扩展这些算法。这突出了ACME的主要优点之一，即它可用于实现大型，分布式的RL算法，这些算法可以以较大的尺度运行，同时仍保持该实现的固有可读性。这项工作提出了第二篇文章的版本，恰好与模块化的增加相吻合，对离线，模仿和从演示算法学习以及作为ACME的一部分实现的各种新代理。

Recent work has shown that fine-tuning large pre-trained language models on a collection of tasks described via instructions, a.k.a. instruction-tuning, improves their zero and few-shot generalization to unseen tasks. However, there is a limited understanding of the performance trade-offs of different decisions made during the instruction-tuning process. These decisions include the scale and diversity of the instruction-tuning benchmark, different task sampling strategies, fine-tuning with and without demonstrations, training using specialized datasets for reasoning and dialogue, and finally, the fine-tuning objectives themselves. In this paper, we characterize the effect of instruction-tuning decisions on downstream task performance when scaling both model and benchmark sizes. To this end, we create OPT-IML Bench: a large benchmark for Instruction Meta-Learning (IML) of 2000 NLP tasks consolidated into task categories from 8 existing benchmarks, and prepare an evaluation framework to measure three types of model generalizations: to tasks from fully held-out categories, to held-out tasks from seen categories, and to held-out instances from seen tasks. Through the lens of this framework, we first present insights about instruction-tuning decisions as applied to OPT-30B and further exploit these insights to train OPT-IML 30B and 175B, which are instruction-tuned versions of OPT. OPT-IML demonstrates all three generalization abilities at both scales on four different evaluation benchmarks with diverse tasks and input formats -- PromptSource, FLAN, Super-NaturalInstructions, and UnifiedSKG. Not only does it significantly outperform OPT on all benchmarks but is also highly competitive with existing models fine-tuned on each specific benchmark. We release OPT-IML at both scales, together with the OPT-IML Bench evaluation framework.

Legal contracts, such as employment or lease agreements, are important documents as they govern the obligations and entitlements of the various contracting parties. However, these documents are typically long and written in legalese resulting in lots of manual hours spent in understanding them. In this paper, we address the task of summarizing legal contracts for each of the contracting parties, to enable faster reviewing and improved understanding of them. Specifically, we collect a dataset consisting of pairwise importance comparison annotations by legal experts for ~293K sentence pairs from lease agreements. We propose a novel extractive summarization system to automatically produce a summary consisting of the most important obligations, entitlements, and prohibitions in a contract. It consists of two modules: (1) a content categorize to identify sentences containing each of the categories (i.e., obligation, entitlement, and prohibition) for a party, and (2) an importance ranker to compare the importance among sentences of each category for a party to obtain a ranked list. The final summary is produced by selecting the most important sentences of a category for each of the parties. We demonstrate the effectiveness of our proposed system by comparing it against several text ranking baselines via automatic and human evaluation.

Project Loon is a Google initiated research project from the Google X Lab. The project focuses on providing remote internet access and network connectivity. The connectivity is established in vertical and horizontal space; vertical connectivity between Google Access Point (GAP) and the balloons, and between balloons and antennas installed at land; horizontal connectivity is between the balloons. This research focuses on the connectivity between the balloons in a mesh network. The proposal focuses on implementing graphical methods like convex hull with adhoc communication protocols. The proposed protocol includes content-based multicasting using angular sector division rather than grids, along with dynamic core-based mesh protocol defining certain core active nodes and passive nodes forming the convex hull. The transmission (multicasting and broadcasting) between the nodes will be evaluated using the link probability defining the probability of the link between two nodes failing. Based on the link probability and node features, best path between transmitting and receiver nodes will be evaluated.

Climate change, population growth, and water scarcity present unprecedented challenges for agriculture. This project aims to forecast soil moisture using domain knowledge and machine learning for crop management decisions that enable sustainable farming. Traditional methods for predicting hydrological response features require significant computational time and expertise. Recent work has implemented machine learning models as a tool for forecasting hydrological response features, but these models neglect a crucial component of traditional hydrological modeling that spatially close units can have vastly different hydrological responses. In traditional hydrological modeling, units with similar hydrological properties are grouped together and share model parameters regardless of their spatial proximity. Inspired by this domain knowledge, we have constructed a novel domain-inspired temporal graph convolution neural network. Our approach involves clustering units based on time-varying hydrological properties, constructing graph topologies for each cluster, and forecasting soil moisture using graph convolutions and a gated recurrent neural network. We have trained, validated, and tested our method on field-scale time series data consisting of approximately 99,000 hydrological response units spanning 40 years in a case study in northeastern United States. Comparison with existing models illustrates the effectiveness of using domain-inspired clustering with time series graph neural networks. The framework is being deployed as part of a pro bono social impact program. The trained models are being deployed on small-holding farms in central Texas.

ML-based motion planning is a promising approach to produce agents that exhibit complex behaviors, and automatically adapt to novel environments. In the context of autonomous driving, it is common to treat all available training data equally. However, this approach produces agents that do not perform robustly in safety-critical settings, an issue that cannot be addressed by simply adding more data to the training set - we show that an agent trained using only a 10% subset of the data performs just as well as an agent trained on the entire dataset. We present a method to predict the inherent difficulty of a driving situation given data collected from a fleet of autonomous vehicles deployed on public roads. We then demonstrate that this difficulty score can be used in a zero-shot transfer to generate curricula for an imitation-learning based planning agent. Compared to training on the entire unbiased training dataset, we show that prioritizing difficult driving scenarios both reduces collisions by 15% and increases route adherence by 14% in closed-loop evaluation, all while using only 10% of the training data.

We study politeness phenomena in nine typologically diverse languages. Politeness is an important facet of communication and is sometimes argued to be cultural-specific, yet existing computational linguistic study is limited to English. We create TyDiP, a dataset containing three-way politeness annotations for 500 examples in each language, totaling 4.5K examples. We evaluate how well multilingual models can identify politeness levels -- they show a fairly robust zero-shot transfer ability, yet fall short of estimated human accuracy significantly. We further study mapping the English politeness strategy lexicon into nine languages via automatic translation and lexicon induction, analyzing whether each strategy's impact stays consistent across languages. Lastly, we empirically study the complicated relationship between formality and politeness through transfer experiments. We hope our dataset will support various research questions and applications, from evaluating multilingual models to constructing polite multilingual agents.

Microprocessor architects are increasingly resorting to domain-specific customization in the quest for high-performance and energy-efficiency. As the systems grow in complexity, fine-tuning architectural parameters across multiple sub-systems (e.g., datapath, memory blocks in different hierarchies, interconnects, compiler optimization, etc.) quickly results in a combinatorial explosion of design space. This makes domain-specific customization an extremely challenging task. Prior work explores using reinforcement learning (RL) and other optimization methods to automatically explore the large design space. However, these methods have traditionally relied on single-agent RL/ML formulations. It is unclear how scalable single-agent formulations are as we increase the complexity of the design space (e.g., full stack System-on-Chip design). Therefore, we propose an alternative formulation that leverages Multi-Agent RL (MARL) to tackle this problem. The key idea behind using MARL is an observation that parameters across different sub-systems are more or less independent, thus allowing a decentralized role assigned to each agent. We test this hypothesis by designing domain-specific DRAM memory controller for several workload traces. Our evaluation shows that the MARL formulation consistently outperforms single-agent RL baselines such as Proximal Policy Optimization and Soft Actor-Critic over different target objectives such as low power and latency. To this end, this work opens the pathway for new and promising research in MARL solutions for hardware architecture search.

We are interested in neurosymbolic systems consisting of a high-level symbolic layer for explainable prediction in terms of human-intelligible concepts; and a low-level neural layer for extracting symbols required to generate the symbolic explanation. Real data is often imperfect meaning that even if the symbolic theory remains unchanged, we may still need to address the problem of mapping raw data to high-level symbols, each time there is a change in the data acquisition environment or equipment. Manual (re-)annotation of the raw data each time this happens is laborious and expensive; and automated labelling methods are often imperfect, especially for complex problems. NEUROLOG proposed the use of a semantic loss function that allows an existing feature-based symbolic model to guide the extraction of feature-values from raw data, using `abduction'. However, the experiments demonstrating the use of semantic loss through abduction appear to rely heavily on a domain-specific pre-processing step that enables a prior delineation of feature locations in the raw data. We examine the use of semantic loss in domains where such pre-processing is not possible, or is not obvious. We show that without any prior information about the features, the NEUROLOG approach can continue to predict accurately even with substantially incorrect feature predictions. We show also that prior information about the features in the form of even imperfect pre-training can help correct this situation. These findings are replicated on the original problem considered by NEUROLOG, without the use of feature-delineation. This suggests that symbolic explanations constructed for data in a domain could be re-used in a related domain, by `feature-adaptation' of pre-trained neural extractors using the semantic loss function constrained by abductive feedback.