Inferring reward functions from human behavior is at the center of value alignment - aligning AI objectives with what we, humans, actually want. But doing so relies on models of how humans behave given their objectives. After decades of research in cognitive science, neuroscience, and behavioral economics, obtaining accurate human models remains an open research topic. This begs the question: how accurate do these models need to be in order for the reward inference to be accurate? On the one hand, if small errors in the model can lead to catastrophic error in inference, the entire framework of reward learning seems ill-fated, as we will never have perfect models of human behavior. On the other hand, if as our models improve, we can have a guarantee that reward accuracy also improves, this would show the benefit of more work on the modeling side. We study this question both theoretically and empirically. We do show that it is unfortunately possible to construct small adversarial biases in behavior that lead to arbitrarily large errors in the inferred reward. However, and arguably more importantly, we are also able to identify reasonable assumptions under which the reward inference error can be bounded linearly in the error in the human model. Finally, we verify our theoretical insights in discrete and continuous control tasks with simulated and human data.

最近出现了变异推断，成为大规模贝叶斯推理中古典马尔特·卡洛（MCMC）的流行替代品。变异推断的核心思想是贸易统计准确性以达到计算效率。它旨在近似后部，以降低计算成本，但可能损害其统计准确性。在这项工作中，我们通过推论模型选择中的案例研究研究了这种统计和计算权衡。侧重于具有对角和低级精度矩阵的高斯推论模型（又名变异近似族），我们在两个方面启动了对权衡的理论研究，贝叶斯后期推断误差和频繁的不确定性不确定定量误差。从贝叶斯后推理的角度来看，我们表征了相对于精确后部的变异后部的误差。我们证明，鉴于固定的计算预算，较低的推论模型会产生具有较高统计近似误差的变异后期，但计算误差较低。它减少了随机优化的方差，进而加速收敛。从频繁的不确定性定量角度来看，我们将变异后部的精度矩阵视为不确定性估计值。我们发现，相对于真实的渐近精度，变异近似遭受了来自数据的采样不确定性的附加统计误差。此外，随着计算预算的增加，这种统计误差成为主要因素。结果，对于小型数据集，推论模型不必全等级即可达到最佳估计误差。我们最终证明了在经验研究之间的这些统计和计算权衡推论，从而证实了理论发现。

奖励黑客 - RL代理商在错过奖励功能中利用差距 - 已被广泛观察到，但尚未系统地研究。要了解如何批量奖励，我们会构建具有误报奖励的四个RL环境。我们调查奖励黑客作为代理能力的函数：模型容量，动作空间分辨率，观察空间噪声和培训时间。更有能力的代理经常利用奖励拼写错误，实现更高的代理奖励和较低的真正奖励，而不是更有技能的代理商。此外，我们发现阶段转换的实例：代理人的行为定性转移的能力阈值，导致真正奖励的急剧下降。这种相转变对监测ML系统的安全构成挑战。为了解决这个问题，我们提出了异常策略的异常检测任务，并提供了几个基线探测器。

Code generation models have achieved impressive performance. However, they tend to be brittle as slight edits to a prompt could lead to very different generations; these robustness properties, critical for user experience when deployed in real-life applications, are not well understood. Most existing works on robustness in text or code tasks have focused on classification, while robustness in generation tasks is an uncharted area and to date there is no comprehensive benchmark for robustness in code generation. In this paper, we propose ReCode, a comprehensive robustness evaluation benchmark for code generation models. We customize over 30 transformations specifically for code on docstrings, function and variable names, code syntax, and code format. They are carefully designed to be natural in real-life coding practice, preserve the original semantic meaning, and thus provide multifaceted assessments of a model's robustness performance. With human annotators, we verified that over 90% of the perturbed prompts do not alter the semantic meaning of the original prompt. In addition, we define robustness metrics for code generation models considering the worst-case behavior under each type of perturbation, taking advantage of the fact that executing the generated code can serve as objective evaluation. We demonstrate ReCode on SOTA models using HumanEval, MBPP, as well as function completion tasks derived from them. Interesting observations include: better robustness for CodeGen over InCoder and GPT-J; models are most sensitive to syntax perturbations; more challenging robustness evaluation on MBPP over HumanEval.

While pre-trained language models (LM) for code have achieved great success in code completion, they generate code conditioned only on the contents within the file, i.e., in-file context, but ignore the rich semantics in other files within the same project, i.e., cross-file context, a critical source of information that is especially useful in modern modular software development. Such overlooking constrains code language models' capacity in code completion, leading to unexpected behaviors such as generating hallucinated class member functions or function calls with unexpected arguments. In this work, we develop a cross-file context finder tool, CCFINDER, that effectively locates and retrieves the most relevant cross-file context. We propose CoCoMIC, a framework that incorporates cross-file context to learn the in-file and cross-file context jointly on top of pretrained code LMs. CoCoMIC successfully improves the existing code LM with a 19.30% relative increase in exact match and a 15.41% relative increase in identifier matching for code completion when the cross-file context is provided.

In consequential decision-making applications, mitigating unwanted biases in machine learning models that yield systematic disadvantage to members of groups delineated by sensitive attributes such as race and gender is one key intervention to strive for equity. Focusing on demographic parity and equality of opportunity, in this paper we propose an algorithm that improves the fairness of a pre-trained classifier by simply dropping carefully selected training data points. We select instances based on their influence on the fairness metric of interest, computed using an infinitesimal jackknife-based approach. The dropping of training points is done in principle, but in practice does not require the model to be refit. Crucially, we find that such an intervention does not substantially reduce the predictive performance of the model but drastically improves the fairness metric. Through careful experiments, we evaluate the effectiveness of the proposed approach on diverse tasks and find that it consistently improves upon existing alternatives.

In unstructured environments, robots run the risk of unexpected collisions. How well they react to these events is determined by how transparent they are to collisions. Transparency is affected by structural properties as well as sensing and control architectures. In this paper, we propose the collision reflex metric as a way to formally quantify transparency. It is defined as the total impulse transferred in collision, which determines the collision mitigation capabilities of a closed-loop robotic system taking into account structure, sensing, and control. We analyze the effect of motor scaling, stiffness, and configuration on the collision reflex of a system using an analytical model. Physical experiments using the move-until-touch behavior are conducted to compare the collision reflex of direct-drive and quasi-direct-drive actuators and robotic hands (Schunk WSG-50 and Dexterous DDHand.) For transparent systems, we see a counter-intuitive trend: the impulse may be lower at higher pre-impact velocities.

资源说明框架（RDF）和属性图（PG）是表示，存储和查询图数据的两个最常用的数据模型。我们提出了表达推理图存储（ERGS） - 构建在Janusgraph（属性图存储）顶部的图存储，该图还允许存储和查询RDF数据集。首先，我们描述了如何将RDF数据转换为属性图表示，然后描述将SPARQL查询转换为一系列Gremlin遍历的查询翻译模块。因此，开发的转换器和翻译器可以允许任何Apache TinkerPop符合图形数据库存储和查询RDF数据集。我们证明了使用JanusGraph作为基本属性图存储的建议方法的有效性，并将其性能与标准RDF系统进行比较。

分类脑电图（EEG）信号有助于理解脑部计算机界面（BCI）。脑电图信号对于研究人类思维的运作方式至关重要。在本文中，我们使用了一个算术计算数据集，该数据集由计算信号（BC）和计算信号（DC）组成。数据集由36位参与者组成。为了了解大脑中神经元的功能，我们对BCS与DCS进行了分类。对于此分类，我们提取了各种特征，例如相互信息（MI），相位锁定值（PLV）和熵置换熵，光谱熵，奇异值分解熵，近似熵，样品熵。这些功能的分类是使用基于RNN的分类器（例如LSTM，BLSTM，ConvlSTM和CNN-LSTM）完成的。当将熵用作特征并作为分类器时，该模型的精度为99.72％。

在结果决策中使用机器学习模型通常会加剧社会不平等，特别是对种族和性别定义的边缘化群体成员产生不同的影响。 ROC曲线（AUC）下的区域被广泛用于评估机器学习中评分功能的性能，但与其他性能指标相比，在算法公平性中进行了研究。由于AUC的成对性质，定义基于AUC的组公平度量是成对依赖性的，并且可能涉及\ emph {group}和\ emph {group} aucs。重要的是，仅考虑一种AUC类别不足以减轻AUC优化的不公平性。在本文中，我们提出了一个最小值学习和偏置缓解框架，该框架既包含组内和组间AUC，同时保持实用性。基于这个Rawlsian框架，我们设计了一种有效的随机优化算法，并证明了其收敛到最小组级AUC。我们对合成数据集和现实数据集进行了数值实验，以验证Minimax框架的有效性和所提出的优化算法。