在这项工作中，我们研究了Bellman方程作为价值预测准确性的替代目标的使用。虽然Bellman方程在所有状态行动对上都是由真实值函数唯一求解的，但我们发现Bellman误差（方程式两侧之间的差异）对于值函数的准确性而言是一个差的代理。特别是，我们表明（1）由于从钟声方程的两侧取消，贝尔曼误差的幅度仅与到达真实值函数的距离相关，即使考虑了所有状态行动对，并且（2）在有限的数据制度中，可以通过无限多种次优的解决方案来完全满足钟手方程。这意味着可以最大程度地减少Bellman误差，而无需提高价值函数的准确性。我们通过一系列命题，说明性玩具示例和标准基准域中的经验分析来证明这些现象。

离线强化学习（RL）定义了从固定批次的数据学习的任务。由于来自分发超出操作的值估计的错误，大多数脱机RL算法采用数据集中包含的动作来计算或正规化策略的方法。构建在预先存在的RL算法上，修改使RL算法正常工作的额外复杂性的成本为代价。离线RL算法引入了新的超参数，通常利用辅助组件，例如生成模型，同时调整底层RL算法。在本文中，我们的目标是在实现最小变化的同时进行深度RL算法。我们发现我们可以通过简单地将行为克隆术语添加到在线RL算法的策略更新并归一化数据的策略更新来匹配最先进的离线RL算法的性能。生成的算法是一种简单的实现和曲线基线，而通过去除先前方法的附加计算开销来大于缩短整个运行时间。

Many practical applications of reinforcement learning constrain agents to learn from a fixed batch of data which has already been gathered, without offering further possibility for data collection. In this paper, we demonstrate that due to errors introduced by extrapolation, standard offpolicy deep reinforcement learning algorithms, such as DQN and DDPG, are incapable of learning without data correlated to the distribution under the current policy, making them ineffective for this fixed batch setting. We introduce a novel class of off-policy algorithms, batch-constrained reinforcement learning, which restricts the action space in order to force the agent towards behaving close to on-policy with respect to a subset of the given data. We present the first continuous control deep reinforcement learning algorithm which can learn effectively from arbitrary, fixed batch data, and empirically demonstrate the quality of its behavior in several tasks.

In value-based reinforcement learning methods such as deep Q-learning, function approximation errors are known to lead to overestimated value estimates and suboptimal policies. We show that this problem persists in an actor-critic setting and propose novel mechanisms to minimize its effects on both the actor and the critic. Our algorithm builds on Double Q-learning, by taking the minimum value between a pair of critics to limit overestimation. We draw the connection between target networks and overestimation bias, and suggest delaying policy updates to reduce per-update error and further improve performance. We evaluate our method on the suite of OpenAI gym tasks, outperforming the state of the art in every environment tested.

Data compression is becoming critical for storing scientific data because many scientific applications need to store large amounts of data and post process this data for scientific discovery. Unlike image and video compression algorithms that limit errors to primary data, scientists require compression techniques that accurately preserve derived quantities of interest (QoIs). This paper presents a physics-informed compression technique implemented as an end-to-end, scalable, GPU-based pipeline for data compression that addresses this requirement. Our hybrid compression technique combines machine learning techniques and standard compression methods. Specifically, we combine an autoencoder, an error-bounded lossy compressor to provide guarantees on raw data error, and a constraint satisfaction post-processing step to preserve the QoIs within a minimal error (generally less than floating point error). The effectiveness of the data compression pipeline is demonstrated by compressing nuclear fusion simulation data generated by a large-scale fusion code, XGC, which produces hundreds of terabytes of data in a single day. Our approach works within the ADIOS framework and results in compression by a factor of more than 150 while requiring only a few percent of the computational resources necessary for generating the data, making the overall approach highly effective for practical scenarios.

Algorithms that involve both forecasting and optimization are at the core of solutions to many difficult real-world problems, such as in supply chains (inventory optimization), traffic, and in the transition towards carbon-free energy generation in battery/load/production scheduling in sustainable energy systems. Typically, in these scenarios we want to solve an optimization problem that depends on unknown future values, which therefore need to be forecast. As both forecasting and optimization are difficult problems in their own right, relatively few research has been done in this area. This paper presents the findings of the ``IEEE-CIS Technical Challenge on Predict+Optimize for Renewable Energy Scheduling," held in 2021. We present a comparison and evaluation of the seven highest-ranked solutions in the competition, to provide researchers with a benchmark problem and to establish the state of the art for this benchmark, with the aim to foster and facilitate research in this area. The competition used data from the Monash Microgrid, as well as weather data and energy market data. It then focused on two main challenges: forecasting renewable energy production and demand, and obtaining an optimal schedule for the activities (lectures) and on-site batteries that lead to the lowest cost of energy. The most accurate forecasts were obtained by gradient-boosted tree and random forest models, and optimization was mostly performed using mixed integer linear and quadratic programming. The winning method predicted different scenarios and optimized over all scenarios jointly using a sample average approximation method.

Search and Rescue (SAR) missions in remote environments often employ autonomous multi-robot systems that learn, plan, and execute a combination of local single-robot control actions, group primitives, and global mission-oriented coordination and collaboration. Often, SAR coordination strategies are manually designed by human experts who can remotely control the multi-robot system and enable semi-autonomous operations. However, in remote environments where connectivity is limited and human intervention is often not possible, decentralized collaboration strategies are needed for fully-autonomous operations. Nevertheless, decentralized coordination may be ineffective in adversarial environments due to sensor noise, actuation faults, or manipulation of inter-agent communication data. In this paper, we propose an algorithmic approach based on adversarial multi-agent reinforcement learning (MARL) that allows robots to efficiently coordinate their strategies in the presence of adversarial inter-agent communications. In our setup, the objective of the multi-robot team is to discover targets strategically in an obstacle-strewn geographical area by minimizing the average time needed to find the targets. It is assumed that the robots have no prior knowledge of the target locations, and they can interact with only a subset of neighboring robots at any time. Based on the centralized training with decentralized execution (CTDE) paradigm in MARL, we utilize a hierarchical meta-learning framework to learn dynamic team-coordination modalities and discover emergent team behavior under complex cooperative-competitive scenarios. The effectiveness of our approach is demonstrated on a collection of prototype grid-world environments with different specifications of benign and adversarial agents, target locations, and agent rewards.

Lack of factual correctness is an issue that still plagues state-of-the-art summarization systems despite their impressive progress on generating seemingly fluent summaries. In this paper, we show that factual inconsistency can be caused by irrelevant parts of the input text, which act as confounders. To that end, we leverage information-theoretic measures of causal effects to quantify the amount of confounding and precisely quantify how they affect the summarization performance. Based on insights derived from our theoretical results, we design a simple multi-task model to control such confounding by leveraging human-annotated relevant sentences when available. Crucially, we give a principled characterization of data distributions where such confounding can be large thereby necessitating the use of human annotated relevant sentences to generate factual summaries. Our approach improves faithfulness scores by 20\% over strong baselines on AnswerSumm \citep{fabbri2021answersumm}, a conversation summarization dataset where lack of faithfulness is a significant issue due to the subjective nature of the task. Our best method achieves the highest faithfulness score while also achieving state-of-the-art results on standard metrics like ROUGE and METEOR. We corroborate these improvements through human evaluation.

As language models (LMs) scale, they develop many novel behaviors, good and bad, exacerbating the need to evaluate how they behave. Prior work creates evaluations with crowdwork (which is time-consuming and expensive) or existing data sources (which are not always available). Here, we automatically generate evaluations with LMs. We explore approaches with varying amounts of human effort, from instructing LMs to write yes/no questions to making complex Winogender schemas with multiple stages of LM-based generation and filtering. Crowdworkers rate the examples as highly relevant and agree with 90-100% of labels, sometimes more so than corresponding human-written datasets. We generate 154 datasets and discover new cases of inverse scaling where LMs get worse with size. Larger LMs repeat back a dialog user's preferred answer ("sycophancy") and express greater desire to pursue concerning goals like resource acquisition and goal preservation. We also find some of the first examples of inverse scaling in RL from Human Feedback (RLHF), where more RLHF makes LMs worse. For example, RLHF makes LMs express stronger political views (on gun rights and immigration) and a greater desire to avoid shut down. Overall, LM-written evaluations are high-quality and let us quickly discover many novel LM behaviors.

This paper describes Waymo's Collision Avoidance Testing (CAT) methodology: a scenario-based testing method that evaluates the safety of the Waymo Driver Automated Driving Systems' (ADS) intended functionality in conflict situations initiated by other road users that require urgent evasive maneuvers. Because SAE Level 4 ADS are responsible for the dynamic driving task (DDT), when engaged, without immediate human intervention, evaluating a Level 4 ADS using scenario-based testing is difficult due to the potentially infinite number of operational scenarios in which hazardous situations may unfold. To that end, in this paper we first describe the safety test objectives for the CAT methodology, including the collision and serious injury metrics and the reference behavior model representing a non-impaired eyes on conflict human driver used to form an acceptance criterion. Afterward, we introduce the process for identifying potentially hazardous situations from a combination of human data, ADS testing data, and expert knowledge about the product design and associated Operational Design Domain (ODD). The test allocation and execution strategy is presented next, which exclusively utilize simulations constructed from sensor data collected on a test track, real-world driving, or from simulated sensor data. The paper concludes with the presentation of results from applying CAT to the fully autonomous ride-hailing service that Waymo operates in San Francisco, California and Phoenix, Arizona. The iterative nature of scenario identification, combined with over ten years of experience of on-road testing, results in a scenario database that converges to a representative set of responder role scenarios for a given ODD. Using Waymo's virtual test platform, which is calibrated to data collected as part of many years of ADS development, the CAT methodology provides a robust and scalable safety evaluation.