标准深度强化学习（DRL）旨在考虑收集的经验在制定政策方面的经验，旨在最大程度地提高预期奖励。这与人类决策不同，在人类的决策中，收益和损失的重视程度有所不同，而外围的结果被越来越多。它也无法利用通过合并分配环境来提高安全性和/或绩效的机会。已经研究了几种分配DRL的方法，其中一种流行的策略是评估预计的可能行动收益分配。我们提出了一种更直接的方法，通过优化了根据全剧集奖励的分布累积分布函数（CDF）指定的风险敏感目标。这种方法允许根据相对质量权衡结果，可用于连续和离散的动作空间，并且自然可以在约束和不受约束的设置中应用。我们展示了如何通过抽样来计算广泛的风险敏感目标的政策梯度的渐近一致估计，随后纳入了降低方差和正则化措施，以促进有效的实质性学习。然后，我们证明使用中等“悲观”的风险概况，强调了代理商表现不佳的场景，从而导致了增强的探索，并不断地专注于解决缺陷。我们在六个OpenAI安全健身房环境中使用不同的风险概况测试了该方法，与最先进的政策方法相比。没有成本限制，我们发现悲观的风险概况可用于降低成本，同时改善总奖励积累。借助成本限制，他们可以以规定的允许成本提供比风险中立的方法更高的积极奖励。

大多数深度加强学习（DRL）的方法试图一次解决单一任务。因此，大多数现有的研究基准组成包括具有普通接口，但在其感知特征，目标或奖励结构中重叠的单独游戏或套房。促进培训代理人的知识转移（例如，通过多任务和元学习），需要更多的环境套件，提供具有足够共同的可配置任务，以共同研究待研究。在本文中，我们提供了Meta Arcade，该工具可以轻松定义和配置共享公共视觉效果，状态空间，动作空间，游戏组件和评分机制的自定义2D街机游戏。元拱门与现有环境不同，因为任职性共性和可配置性都优先考虑：可以从公共元素构建整组游戏，并且这些元素可通过暴露参数调节。我们包括一套24个预定义的游戏，共同说明了该框架的可能性，并讨论如何为研究应用程序配置这些游戏。我们提供了几个实验，说明了可以使用Meta Arcade如何使用，包括预定义游戏的单项任务基准，以设定的时间表更改游戏参数的示例课程的方法，以及游戏之间的转移学习探索。

人类感知机器人导航有一系列应用程序，其中移动机器人对普通人类环境中的人们带来多功能援助。虽然现有研究主要集中在以独立，故意个人为独立的，但人们进入群体;因此，移动机器人必须在围绕人们时尊重人群。本文探讨了使用深度加强学习的基于动态组形成的学习群体感知导航策略。通过仿真实验，我们展示了与忽视人类群体的基线政策相比，群体感知政策实现了更大的机器人导航性能（例如，较少的碰撞），尽量减少侵犯社会规范和不适，并减少机器人对行人的运动影响。我们的成果有助于发展社会导航和移动机器人将移动机器人集成到人类环境中。

Markowitz mean-variance portfolios with sample mean and covariance as input parameters feature numerous issues in practice. They perform poorly out of sample due to estimation error, they experience extreme weights together with high sensitivity to change in input parameters. The heavy-tail characteristics of financial time series are in fact the cause for these erratic fluctuations of weights that consequently create substantial transaction costs. In robustifying the weights we present a toolbox for stabilizing costs and weights for global minimum Markowitz portfolios. Utilizing a projected gradient descent (PGD) technique, we avoid the estimation and inversion of the covariance operator as a whole and concentrate on robust estimation of the gradient descent increment. Using modern tools of robust statistics we construct a computationally efficient estimator with almost Gaussian properties based on median-of-means uniformly over weights. This robustified Markowitz approach is confirmed by empirical studies on equity markets. We demonstrate that robustified portfolios reach the lowest turnover compared to shrinkage-based and constrained portfolios while preserving or slightly improving out-of-sample performance.

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.

As AI systems become more capable, we would like to enlist their help to supervise other AIs. We experiment with methods for training a harmless AI assistant through self-improvement, without any human labels identifying harmful outputs. The only human oversight is provided through a list of rules or principles, and so we refer to the method as 'Constitutional AI'. The process involves both a supervised learning and a reinforcement learning phase. In the supervised phase we sample from an initial model, then generate self-critiques and revisions, and then finetune the original model on revised responses. In the RL phase, we sample from the finetuned model, use a model to evaluate which of the two samples is better, and then train a preference model from this dataset of AI preferences. We then train with RL using the preference model as the reward signal, i.e. we use 'RL from AI Feedback' (RLAIF). As a result we are able to train a harmless but non-evasive AI assistant that engages with harmful queries by explaining its objections to them. Both the SL and RL methods can leverage chain-of-thought style reasoning to improve the human-judged performance and transparency of AI decision making. These methods make it possible to control AI behavior more precisely and with far fewer human labels.

Adversarial attacks hamper the decision-making ability of neural networks by perturbing the input signal. The addition of calculated small distortion to images, for instance, can deceive a well-trained image classification network. In this work, we propose a novel attack technique called Sparse Adversarial and Interpretable Attack Framework (SAIF). Specifically, we design imperceptible attacks that contain low-magnitude perturbations at a small number of pixels and leverage these sparse attacks to reveal the vulnerability of classifiers. We use the Frank-Wolfe (conditional gradient) algorithm to simultaneously optimize the attack perturbations for bounded magnitude and sparsity with $O(1/\sqrt{T})$ convergence. Empirical results show that SAIF computes highly imperceptible and interpretable adversarial examples, and outperforms state-of-the-art sparse attack methods on the ImageNet dataset.

Medical treatments tailored to a patient's baseline characteristics hold the potential of improving patient outcomes while reducing negative side effects. Learning individualized treatment rules (ITRs) often requires aggregation of multiple datasets(sites); however, current ITR methodology does not take between-site heterogeneity into account, which can hurt model generalizability when deploying back to each site. To address this problem, we develop a method for individual-level meta-analysis of ITRs, which jointly learns site-specific ITRs while borrowing information about feature sign-coherency via a scientifically-motivated directionality principle. We also develop an adaptive procedure for model tuning, using information criteria tailored to the ITR learning problem. We study the proposed methods through numerical experiments to understand their performance under different levels of between-site heterogeneity and apply the methodology to estimate ITRs in a large multi-center database of electronic health records. This work extends several popular methodologies for estimating ITRs (A-learning, weighted learning) to the multiple-sites setting.

This paper is a technical overview of DeepMind and Google's recent work on reinforcement learning for controlling commercial cooling systems. Building on expertise that began with cooling Google's data centers more efficiently, we recently conducted live experiments on two real-world facilities in partnership with Trane Technologies, a building management system provider. These live experiments had a variety of challenges in areas such as evaluation, learning from offline data, and constraint satisfaction. Our paper describes these challenges in the hope that awareness of them will benefit future applied RL work. We also describe the way we adapted our RL system to deal with these challenges, resulting in energy savings of approximately 9% and 13% respectively at the two live experiment sites.

Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions. While these capabilities have led to widespread adoption, most LLMs are developed by resource-rich organizations and are frequently kept from the public. As a step towards democratizing this powerful technology, we present BLOOM, a 176B-parameter open-access language model designed and built thanks to a collaboration of hundreds of researchers. BLOOM is a decoder-only Transformer language model that was trained on the ROOTS corpus, a dataset comprising hundreds of sources in 46 natural and 13 programming languages (59 in total). We find that BLOOM achieves competitive performance on a wide variety of benchmarks, with stronger results after undergoing multitask prompted finetuning. To facilitate future research and applications using LLMs, we publicly release our models and code under the Responsible AI License.