We study the learning dynamics of self-predictive learning for reinforcement learning, a family of algorithms that learn representations by minimizing the prediction error of their own future latent representations. Despite its recent empirical success, such algorithms have an apparent defect: trivial representations (such as constants) minimize the prediction error, yet it is obviously undesirable to converge to such solutions. Our central insight is that careful designs of the optimization dynamics are critical to learning meaningful representations. We identify that a faster paced optimization of the predictor and semi-gradient updates on the representation, are crucial to preventing the representation collapse. Then in an idealized setup, we show self-predictive learning dynamics carries out spectral decomposition on the state transition matrix, effectively capturing information of the transition dynamics. Building on the theoretical insights, we propose bidirectional self-predictive learning, a novel self-predictive algorithm that learns two representations simultaneously. We examine the robustness of our theoretical insights with a number of small-scale experiments and showcase the promise of the novel representation learning algorithm with large-scale experiments.

分享自治是指使自治工人能够与人类合作的方法，以提高人类性能。然而，除了提高性能之外，它通常也可能是有益的，代理同时考虑保留用户的经验或合作满意度。为了解决这一额外目标，我们通过约束自主代理的干预次数来研究改进用户体验的方法。我们提出了两种无模型的加强学习方法，可以考虑到干预措施的艰难和软限制。我们表明，我们的方法不仅表现出现有的基线，而且还消除了手动调整黑匣子超参数，以控制援助水平。我们还提供了对干预情景的深入分析，以进一步照亮系统理解。

许多连续的决策问题是使用使用其他一些策略收集的历史数据，需要使用历史数据的高赌注并要求新策略（OPE）。提供无偏估计的最常见的OPE技术之一是基于轨迹的重要性采样（是）。但是，由于轨迹的高方差是估计，最近通过了基于国家行动探索分布（SIS）的重要性采样方法。不幸的是，虽然SIS经常为长视野提供较低的方差估计，但估算状态行动分配比可能是具有挑战性的并且导致偏差估计。在本文中，我们对该偏差差异进行了新的视角，并显示了存在终点是SIS的估计频谱的存在。此外，我们还建立了这些估算器的双重强大和加权版本的频谱。我们提供了经验证据，即该频谱中的估计值可用于在IS和SIS的偏差和方差之间进行折衷，并且可以实现比两者和SIS更低的平均平方误差。

面对顺序决策问题时，能够预测如果使用新策略进行决策会发生什么会发生什么。这些预测通常必须基于在一些先前使用的决策规则下收集的数据。许多以前的方法使得这种违规（或反事实）估计的性能测量值的预期值称为返回。在本文中，我们采取了迈向普遍违规估算机（UNO）的第一步 - 为返回分配的任何参数提供截止政策估计和高信任界限。我们使用UNO来估计和同时限制均值，方差，量级/中位数，分位式范围，CVAR和返回的整个累积分布。最后，我们还在各种环境中讨论了UNO的适用性，包括完全可观察，部分可观察的（即，与未观察到的混乱），马尔可夫，非马尔可瓦尔，静止，平稳的非稳定性和离散分布转移。

We propose the fully differentiable $\nabla$-RANSAC.It predicts the inlier probabilities of the input data points, exploits the predictions in a guided sampler, and estimates the model parameters (e.g., fundamental matrix) and its quality while propagating the gradients through the entire procedure. The random sampler in $\nabla$-RANSAC is based on a clever re-parametrization strategy, i.e.\ the Gumbel Softmax sampler, that allows propagating the gradients directly into the subsequent differentiable minimal solver. The model quality function marginalizes over the scores from all models estimated within $\nabla$-RANSAC to guide the network learning accurate and useful probabilities.$\nabla$-RANSAC is the first to unlock the end-to-end training of geometric estimation pipelines, containing feature detection, matching and RANSAC-like randomized robust estimation. As a proof of its potential, we train $\nabla$-RANSAC together with LoFTR, i.e. a recent detector-free feature matcher, to find reliable correspondences in an end-to-end manner. We test $\nabla$-RANSAC on a number of real-world datasets on fundamental and essential matrix estimation. It is superior to the state-of-the-art in terms of accuracy while being among the fastest methods. The code and trained models will be made public.

Our earlier research built a virtual shake robot in simulation to study the dynamics of precariously balanced rocks (PBR), which are negative indicators of earthquakes in nature. The simulation studies need validation through physical experiments. For this purpose, we developed Shakebot, a low-cost (under $2,000), open-source shake table to validate simulations of PBR dynamics and facilitate other ground motion experiments. The Shakebot is a custom one-dimensional prismatic robotic system with perception and motion software developed using the Robot Operating System (ROS). We adapted affordable and high-accuracy components from 3D printers, particularly a closed-loop stepper motor for actuation and a toothed belt for transmission. The stepper motor enables the bed to reach a maximum horizontal acceleration of 11.8 m/s^2 (1.2 g), and velocity of 0.5 m/s, when loaded with a 2 kg scale-model PBR. The perception system of the Shakebot consists of an accelerometer and a high frame-rate camera. By fusing camera-based displacements with acceleration measurements, the Shakebot is able to carry out accurate bed velocity estimation. The ROS-based perception and motion software simplifies the transition of code from our previous virtual shake robot to the physical Shakebot. The reuse of the control programs ensures that the implemented ground motions are consistent for both the simulation and physical experiments, which is critical to validate our simulation experiments.

Exploratory data analytics (EDA) is a sequential decision making process where analysts choose subsequent queries that might lead to some interesting insights based on the previous queries and corresponding results. Data processing systems often execute the queries on samples to produce results with low latency. Different downsampling strategy preserves different statistics of the data and have different magnitude of latency reductions. The optimum choice of sampling strategy often depends on the particular context of the analysis flow and the hidden intent of the analyst. In this paper, we are the first to consider the impact of sampling in interactive data exploration settings as they introduce approximation errors. We propose a Deep Reinforcement Learning (DRL) based framework which can optimize the sample selection in order to keep the analysis and insight generation flow intact. Evaluations with 3 real datasets show that our technique can preserve the original insight generation flow while improving the interaction latency, compared to baseline methods.

Transformers are powerful visual learners, in large part due to their conspicuous lack of manually-specified priors. This flexibility can be problematic in tasks that involve multiple-view geometry, due to the near-infinite possible variations in 3D shapes and viewpoints (requiring flexibility), and the precise nature of projective geometry (obeying rigid laws). To resolve this conundrum, we propose a "light touch" approach, guiding visual Transformers to learn multiple-view geometry but allowing them to break free when needed. We achieve this by using epipolar lines to guide the Transformer's cross-attention maps, penalizing attention values outside the epipolar lines and encouraging higher attention along these lines since they contain geometrically plausible matches. Unlike previous methods, our proposal does not require any camera pose information at test-time. We focus on pose-invariant object instance retrieval, where standard Transformer networks struggle, due to the large differences in viewpoint between query and retrieved images. Experimentally, our method outperforms state-of-the-art approaches at object retrieval, without needing pose information at test-time.

Real-world tasks are largely composed of multiple models, each performing a sub-task in a larger chain of tasks, i.e., using the output from a model as input for another model in a multi-model pipeline. A model like MATRa performs the task of Crosslingual Transliteration in two stages, using English as an intermediate transliteration target when transliterating between two indic languages. We propose a novel distillation technique, EPIK, that condenses two-stage pipelines for hierarchical tasks into a single end-to-end model without compromising performance. This method can create end-to-end models for tasks without needing a dedicated end-to-end dataset, solving the data scarcity problem. The EPIK model has been distilled from the MATra model using this technique of knowledge distillation. The MATra model can perform crosslingual transliteration between 5 languages - English, Hindi, Tamil, Kannada and Bengali. The EPIK model executes the task of transliteration without any intermediate English output while retaining the performance and accuracy of the MATra model. The EPIK model can perform transliteration with an average CER score of 0.015 and average phonetic accuracy of 92.1%. In addition, the average time for execution has reduced by 54.3% as compared to the teacher model and has a similarity score of 97.5% with the teacher encoder. In a few cases, the EPIK model (student model) can outperform the MATra model (teacher model) even though it has been distilled from the MATra model.

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.