We consider lexicographic bi-objective problems on Markov Decision Processes (MDPs), where we optimize one objective while guaranteeing optimality of another. We propose a two-stage technique for solving such problems when the objectives are related (in a way that we formalize). We instantiate our technique for two natural pairs of objectives: minimizing the (conditional) expected number of steps to a target while guaranteeing the optimal probability of reaching it; and maximizing the (conditional) expected average reward while guaranteeing an optimal probability of staying safe (w.r.t. some safe set of states). For the first combination of objectives, which covers the classical frozen lake environment from reinforcement learning, we also report on experiments performed using a prototype implementation of our algorithm and compare it with what can be obtained from state-of-the-art probabilistic model checkers solving optimal reachability.
相關內容
Model Predictive Control lacks the ability to escape local minima in nonconvex problems. Furthermore, in fast-changing, uncertain environments, the conventional warmstart, using the optimal trajectory from the last timestep, often falls short of providing an adequately close initial guess for the current optimal trajectory. This can potentially result in convergence failures and safety issues. Therefore, this paper proposes a framework for learning-aided warmstarts of Model Predictive Control algorithms. Our method leverages a neural network based multimodal predictor to generate multiple trajectory proposals for the autonomous vehicle, which are further refined by a sampling-based technique. This combined approach enables us to identify multiple distinct local minima and provide an improved initial guess. We validate our approach with Monte Carlo simulations of traffic scenarios.
This study proposes an Ensemble Differential Evolution with Simula-tion-Based Hybridization and Self-Adaptation (EDESH-SA) approach for inven-tory management (IM) under uncertainty. In this study, DE with multiple runs is combined with a simulation-based hybridization method that includes a self-adaptive mechanism that dynamically alters mutation and crossover rates based on the success or failure of each iteration. Due to its adaptability, the algorithm is able to handle the complexity and uncertainty present in IM. Utilizing Monte Carlo Simulation (MCS), the continuous review (CR) inventory strategy is ex-amined while accounting for stochasticity and various demand scenarios. This simulation-based approach enables a realistic assessment of the proposed algo-rithm's applicability in resolving the challenges faced by IM in practical settings. The empirical findings demonstrate the potential of the proposed method to im-prove the financial performance of IM and optimize large search spaces. The study makes use of performance testing with the Ackley function and Sensitivity Analysis with Perturbations to investigate how changes in variables affect the objective value. This analysis provides valuable insights into the behavior and robustness of the algorithm.
This work studies the problem of learning unbiased algorithms from biased feedback for recommendation. We address this problem from a novel distribution shift perspective. Recent works in unbiased recommendation have advanced the state-of-the-art with various techniques such as re-weighting, multi-task learning, and meta-learning. Despite their empirical successes, most of them lack theoretical guarantees, forming non-negligible gaps between theories and recent algorithms. In this paper, we propose a theoretical understanding of why existing unbiased learning objectives work for unbiased recommendation. We establish a close connection between unbiased recommendation and distribution shift, which shows that existing unbiased learning objectives implicitly align biased training and unbiased test distributions. Built upon this connection, we develop two generalization bounds for existing unbiased learning methods and analyze their learning behavior. Besides, as a result of the distribution shift, we further propose a principled framework, Adversarial Self-Training (AST), for unbiased recommendation. Extensive experiments on real-world and semi-synthetic datasets demonstrate the effectiveness of AST.
In this work, we explore Parameter-Efficient-Learning (PEL) techniques to repurpose a General-Purpose-Speech (GSM) model for Arabic dialect identification (ADI). Specifically, we investigate different setups to incorporate trainable features into a multi-layer encoder-decoder GSM formulation under frozen pre-trained settings. Our architecture includes residual adapter and model reprogramming (input-prompting). We design a token-level label mapping to condition the GSM for Arabic Dialect Identification (ADI). This is challenging due to the high variation in vocabulary and pronunciation among the numerous regional dialects. We achieve new state-of-the-art accuracy on the ADI-17 dataset by vanilla fine-tuning. We further reduce the training budgets with the PEL method, which performs within 1.86% accuracy to fine-tuning using only 2.5% of (extra) network trainable parameters. Our study demonstrates how to identify Arabic dialects using a small dataset and limited computation with open source code and pre-trained models.
In this work, we present novel protocols over rings for semi-honest secure three-party computation (3-PC) and malicious four-party computation (4-PC) with one corruption. Compared to state-of-the-art protocols in the same setting, our protocols require fewer low-latency and high-bandwidth links between the parties to achieve high throughput. Our protocols also reduce the computational complexity by requiring up to 50 percent fewer basic instructions per gate. Further, our protocols achieve the currently best-known communication complexity (3/5 elements per multiplication gate) with an optional preprocessing phase to reduce the communication complexity of the online phase to 2/3 elements per multiplication gate. In homogeneous network settings, i.e. all links between the parties share similar network bandwidth and latency, our protocols achieve up to two times higher throughput than state-of-the-art protocols. In heterogeneous network settings, i.e. all links between the parties share different network bandwidth and latency, our protocols achieve even larger performance improvements. We implemented our protocols and multiple other state-of-the-art protocols in a novel open-source C++ framework optimized for achieving high throughput. All our protocols achieve more than one billion 32-bit multiplication or more than 40 billion AND gates per second. This is the highest throughput achieved in 3-PC and 4-PC so far and more than three orders of magnitude higher than the throughput MP-SPDZ achieves in the same settings.
This work introduces a framework harnessing the capabilities of Large Language Models (LLMs) to generate primitive task conditions for generalizable long-horizon manipulations with novel objects and unseen tasks. These task conditions serve as guides for the generation and adjustment of Dynamic Movement Primitives (DMP) trajectories for long-horizon task execution. We further create a challenging robotic manipulation task suite based on Pybullet for long-horizon task evaluation. Extensive experiments in both simulated and real-world environments demonstrate the effectiveness of our framework on both familiar tasks involving new objects and novel but related tasks, highlighting the potential of LLMs in enhancing robotic system versatility and adaptability. Project website: //object814.github.io/Task-Condition-With-LLM/
Large Language Models (LLMs) have shown promise in the autonomous driving sector, particularly in generalization and interpretability. We introduce a unique object-level multimodal LLM architecture that merges vectorized numeric modalities with a pre-trained LLM to improve context understanding in driving situations. We also present a new dataset of 160k QA pairs derived from 10k driving scenarios, paired with high quality control commands collected with RL agent and question answer pairs generated by teacher LLM (GPT-3.5). A distinct pretraining strategy is devised to align numeric vector modalities with static LLM representations using vector captioning language data. We also introduce an evaluation metric for Driving QA and demonstrate our LLM-driver's proficiency in interpreting driving scenarios, answering questions, and decision-making. Our findings highlight the potential of LLM-based driving action generation in comparison to traditional behavioral cloning. We make our benchmark, datasets, and model available for further exploration.
To maintain a reliable grid we need fast decision-making algorithms for complex problems like Dynamic Reconfiguration (DyR). DyR optimizes distribution grid switch settings in real-time to minimize grid losses and dispatches resources to supply loads with available generation. DyR is a mixed-integer problem and can be computationally intractable to solve for large grids and at fast timescales. We propose GraPhyR, a Physics-Informed Graph Neural Network (GNNs) framework tailored for DyR. We incorporate essential operational and connectivity constraints directly within the GNN framework and train it end-to-end. Our results show that GraPhyR is able to learn to optimize the DyR task.
The problem of Multiple Object Tracking (MOT) consists in following the trajectory of different objects in a sequence, usually a video. In recent years, with the rise of Deep Learning, the algorithms that provide a solution to this problem have benefited from the representational power of deep models. This paper provides a comprehensive survey on works that employ Deep Learning models to solve the task of MOT on single-camera videos. Four main steps in MOT algorithms are identified, and an in-depth review of how Deep Learning was employed in each one of these stages is presented. A complete experimental comparison of the presented works on the three MOTChallenge datasets is also provided, identifying a number of similarities among the top-performing methods and presenting some possible future research directions.
We propose a novel single shot object detection network named Detection with Enriched Semantics (DES). Our motivation is to enrich the semantics of object detection features within a typical deep detector, by a semantic segmentation branch and a global activation module. The segmentation branch is supervised by weak segmentation ground-truth, i.e., no extra annotation is required. In conjunction with that, we employ a global activation module which learns relationship between channels and object classes in a self-supervised manner. Comprehensive experimental results on both PASCAL VOC and MS COCO detection datasets demonstrate the effectiveness of the proposed method. In particular, with a VGG16 based DES, we achieve an mAP of 81.7 on VOC2007 test and an mAP of 32.8 on COCO test-dev with an inference speed of 31.5 milliseconds per image on a Titan Xp GPU. With a lower resolution version, we achieve an mAP of 79.7 on VOC2007 with an inference speed of 13.0 milliseconds per image.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191