Search

Designing control policies for large, distributed systems is challenging, especially in the context of critical, temporal logic based specifications (e.g., safety) that must be met with high probability. Compositional methods for such problems are needed for scalability, yet relying on worst-case assumptions for decomposition tends to be overly conservative. In this work, we use the framework of Constrained Markov Decision Processes (CMDPs) to provide an assume-guarantee based decomposition for synthesizing decentralized control policies, subject to logical constraints in a multi-agent setting. The returned policies are guaranteed to satisfy the constraints with high probability and provide a lower bound on the achieved objective reward. We empirically find the returned policies to achieve near-optimal rewards while enjoying an order of magnitude reduction in problem size and execution time., Comment: 6 pages, 1 figure, accepted for publication at the 63rd IEEE Conf. on Decision and Control (2024)

Distilling conversational skills into Small Language Models (SLMs) with approximately 1 billion parameters presents significant challenges. Firstly, SLMs have limited capacity in their model parameters to learn extensive knowledge compared to larger models. Secondly, high-quality conversational datasets are often scarce, small, and domain-specific. Addressing these challenges, we introduce a novel data distillation framework named CoDi (short for Conversational Distillation, pronounced "Cody"), allowing us to synthesize large-scale, assistant-style datasets in a steerable and diverse manner. Specifically, while our framework is task agnostic at its core, we explore and evaluate the potential of CoDi on the task of conversational grounded reasoning for question answering. This is a typical on-device scenario for specialist SLMs, allowing for open-domain model responses, without requiring the model to "memorize" world knowledge in its limited weights. Our evaluations show that SLMs trained with CoDi-synthesized data achieve performance comparable to models trained on human-annotated data in standard metrics. Additionally, when using our framework to generate larger datasets from web data, our models surpass larger, instruction-tuned models in zero-shot conversational grounded reasoning tasks., Comment: 13 pages

Imitation learning (IL) is notably effective for robotic tasks where directly programming behaviors or defining optimal control costs is challenging. In this work, we address a scenario where the imitator relies solely on observed behavior and cannot make environmental interactions during learning. It does not have additional supplementary datasets beyond the expert's dataset nor any information about the transition dynamics. Unlike state-of-the-art (SOTA) IL methods, this approach tackles the limitations of conventional IL by operating in a more constrained and realistic setting. Our method uses the Markov balance equation and introduces a novel conditional density estimation-based imitation learning framework. It employs conditional normalizing flows for transition dynamics estimation and aims at satisfying a balance equation for the environment. Through a series of numerical experiments on Classic Control and MuJoCo environments, we demonstrate consistently superior empirical performance compared to many SOTA IL algorithms.

Enterprise chatbots, powered by generative AI, are emerging as key applications to enhance employee productivity. Retrieval Augmented Generation (RAG), Large Language Models (LLMs), and orchestration frameworks like Langchain and Llamaindex are crucial for building these chatbots. However, creating effective enterprise chatbots is challenging and requires meticulous RAG pipeline engineering. This includes fine-tuning embeddings and LLMs, extracting documents from vector databases, rephrasing queries, reranking results, designing prompts, honoring document access controls, providing concise responses, including references, safeguarding personal information, and building orchestration agents. We present a framework for building RAG-based chatbots based on our experience with three NVIDIA chatbots: for IT/HR benefits, financial earnings, and general content. Our contributions are three-fold: introducing the FACTS framework (Freshness, Architectures, Cost, Testing, Security), presenting fifteen RAG pipeline control points, and providing empirical results on accuracy-latency tradeoffs between large and small LLMs. To the best of our knowledge, this is the first paper of its kind that provides a holistic view of the factors as well as solutions for building secure enterprise-grade chatbots.", Comment: 8 pages, 6 figures, 2 tables, Preprint submission to ACM CIKM 2024

The fruit identification process involves analyzing and categorizing different types of fruits based on their visual characteristics. This activity can be achieved using a range of methodologies, encompassing manual examination, conventional computer vision methodologies, and more sophisticated methodologies employing machine learning and deep learning. Our study identified a total of 15 distinct categories of fruit, consisting of class Avocado, Banana, Cherry, Apple Braeburn, Apple golden 1, Apricot, Grape, Kiwi, Mango, Orange, Papaya, Peach, Pineapple, Pomegranate and Strawberry. Neural Architecture Search (NAS) is a technological advancement employed within the realm of deep learning and artificial intelligence, to automate conceptualizing and refining neural network topologies. NAS aims to identify neural network structures that are highly suitable for tasks, such as the detection of fruits. Our suggested model with 99.98% mAP increased the detection performance of the preceding research study that used Fruit datasets. In addition, after the completion of the study, a comparative analysis was carried out to assess the findings in conjunction with those of another research that is connected to the topic. When compared to the findings of earlier studies, the detector that was proposed exhibited higher performance in terms of both its accuracy and its precision.

Data plane verification has grown into a powerful tool to ensure network correctness. However, existing monolithic data plane models have high memory requirements with large networks, and the existing method of scaling out is too limited in expressiveness to capture practical network features. In this paper, we describe Scylla, a general data plane verifier that provides fine-grained scale-out without the need for a monolithic network model. Scylla creates models for what we call intent-based slices, each of which is constructed at a fine (rule-level) granularity with just enough to verify a given set of intents. The sliced models are retained in memory across a cluster and are incrementally updated in a distributed compute cluster in response to network updates. Our experiments show that Scylla makes the scaling problem more granular -- tied to the size of the intent-based slices rather than that of the overall network. This enables Scylla to verify large, complex networks in minimum units of work that are significantly smaller (in both memory and time) than past techniques, enabling fast scale-out verification with minimal resource requirement.

In this paper, we introduce the constrained best mixed arm identification (CBMAI) problem with a fixed budget. This is a pure exploration problem in a stochastic finite armed bandit model. Each arm is associated with a reward and multiple types of costs from unknown distributions. Unlike the unconstrained best arm identification problem, the optimal solution for the CBMAI problem may be a randomized mixture of multiple arms. The goal thus is to find the best mixed arm that maximizes the expected reward subject to constraints on the expected costs with a given learning budget $N$. We propose a novel, parameter-free algorithm, called the Score Function-based Successive Reject (SFSR) algorithm, that combines the classical successive reject framework with a novel score-function-based rejection criteria based on linear programming theory to identify the optimal support. We provide a theoretical upper bound on the mis-identification (of the the support of the best mixed arm) probability and show that it decays exponentially in the budget $N$ and some constants that characterize the hardness of the problem instance. We also develop an information theoretic lower bound on the error probability that shows that these constants appropriately characterize the problem difficulty. We validate this empirically on a number of average and hard instances., Comment: 7 pages, 5 figures, 1 table

Understanding how robots plan and execute tasks is crucial in today's world, where they are becoming more prevalent in our daily lives. However, teaching non-experts the complexities of robot planning can be challenging. This work presents an open-source platform that simplifies the process using a visual interface that completely abstracts the complex internals of hierarchical planning that robots use for performing task and motion planning. Using the principles developed in the field of explainable AI, this intuitive platform enables users to create plans for robots to complete tasks, and provides helpful hints and natural language explanations for errors. The platform also has a built-in simulator to demonstrate how robots execute submitted plans. This platform's efficacy was tested in a user study on university students with little to no computer science background. Our results show that this platform is highly effective in teaching novice users the intuitions of robot task planning.

We consider the problem of designing a control policy for an infinite-horizon discounted cost Markov decision process $\mathcal{M}$ when we only have access to an approximate model $\hat{\mathcal{M}}$. How well does an optimal policy $\hat{\pi}^{\star}$ of the approximate model perform when used in the original model $\mathcal{M}$? We answer this question by bounding a weighted norm of the difference between the value function of $\hat{\pi}^\star $ when used in $\mathcal{M}$ and the optimal value function of $\mathcal{M}$. We then extend our results and obtain potentially tighter upper bounds by considering affine transformations of the per-step cost. We further provide upper bounds that explicitly depend on the weighted distance between cost functions and weighted distance between transition kernels of the original and approximate models. We present examples to illustrate our results.

Recent advancements in Large Language Models (LLMs) have been reshaping Natural Language Processing (NLP) task in several domains. Their use in the field of Human Resources (HR) has still room for expansions and could be beneficial for several time consuming tasks. Examples such as time-off submissions, medical claims filing, and access requests are noteworthy, but they are by no means the sole instances. However, the aforementioned developments must grapple with the pivotal challenge of constructing a high-quality training dataset. On one hand, most conversation datasets are solving problems for customers not employees. On the other hand, gathering conversations with HR could raise privacy concerns. To solve it, we introduce HR-Multiwoz, a fully-labeled dataset of 550 conversations spanning 10 HR domains to evaluate LLM Agent. Our work has the following contributions: (1) It is the first labeled open-sourced conversation dataset in the HR domain for NLP research. (2) It provides a detailed recipe for the data generation procedure along with data analysis and human evaluations. The data generation pipeline is transferable and can be easily adapted for labeled conversation data generation in other domains. (3) The proposed data-collection pipeline is mostly based on LLMs with minimal human involvement for annotation, which is time and cost-efficient., Comment: 13 pages, 9 figures

Learning in POMDPs is known to be significantly harder than in MDPs. In this paper, we consider the online learning problem for episodic POMDPs with unknown transition and observation models. We propose a Posterior Sampling-based reinforcement learning algorithm for POMDPs (PS4POMDPs), which is much simpler and more implementable compared to state-of-the-art optimism-based online learning algorithms for POMDPs. We show that the Bayesian regret of the proposed algorithm scales as the square root of the number of episodes and is polynomial in the other parameters. In a general setting, the regret scales exponentially in the horizon length $H$, and we show that this is inevitable by providing a lower bound. However, when the POMDP is undercomplete and weakly revealing (a common assumption in the recent literature), we establish a polynomial Bayesian regret bound. We finally propose a posterior sampling algorithm for multi-agent POMDPs, and show it too has sublinear regret., Comment: 41 pages, 9 figures

During the evacuation of a building, the rapid and accurate tracking of human evacuees can be used by a guide robot to increase the effectiveness of the evacuation [1],[2]. This paper introduces a near real-time human position tracking solution tailored for evacuation robots. Using a pose detector, our system first identifies human joints in the camera frame in near real-time and then translates the position of these pixels into real-world coordinates via a simple calibration process. We run multiple trials of the system in action in an indoor lab environment and show that the system can achieve an accuracy of 0.55 meters when compared to ground truth. The system can also achieve an average of 3 frames per second (FPS) which was sufficient for our study on robot-guided human evacuation. The potential of our approach extends beyond mere tracking, paving the way for evacuee motion prediction, allowing the robot to proactively respond to human movements during an evacuation., Comment: The 2nd Workshop on Social Robot Navigation: Advances and Evaluation. In conjunction with: IEEE International Conference on Intelligent Robots and Systems (IROS 2023)

This paper considers the problem of developing suitable behavior models of human evacuees during a robot-guided emergency evacuation. We describe our recent research developing behavior models of evacuees and potential future uses of these models. This paper considers how behavior models can contribute to the development and design of emergency evacuation simulations in order to improve social navigation during an evacuation., Comment: Presented at Social Robot Navigation: Advances and Evaluation. In conjunction with: IEEE International Conference on Robotics and Automation, ICRA 2022

Imitation Learning (IL) is an important paradigm within the broader reinforcement learning (RL) methodology. Unlike most of RL, it does not assume availability of reward-feedback. Reward inference and shaping are known to be difficult and error-prone methods particularly when the demonstration data comes from human experts. Classical methods such as behavioral cloning and inverse reinforcement learning are highly sensitive to estimation errors, a problem that is particularly acute in continuous state space problems. Meanwhile, state-of-the-art IL algorithms convert behavioral policy learning problems into distribution-matching problems which often require additional online interaction data to be effective. In this paper, we consider the problem of imitation learning in continuous state space environments based solely on observed behavior, without access to transition dynamics information, reward structure, or, most importantly, any additional interactions with the environment. Our approach is based on the Markov balance equation and introduces a novel conditional kernel density estimation-based imitation learning framework. It involves estimating the environment's transition dynamics using conditional kernel density estimators and seeks to satisfy the probabilistic balance equations for the environment. We establish that our estimators satisfy basic asymptotic consistency requirements. Through a series of numerical experiments on continuous state benchmark environments, we show consistently superior empirical performance over many state-of-the-art IL algorithms.

We consider a cooperative multi-agent system consisting of a team of agents with decentralized information. Our focus is on the design of symmetric (i.e. identical) strategies for the agents in order to optimize a finite horizon team objective. We start with a general information structure and then consider some special cases. The constraint of using symmetric strategies introduces new features and complications in the team problem. For example, we show in a simple example that randomized symmetric strategies may outperform deterministic symmetric strategies. We also discuss why some of the known approaches for reducing agents' private information in teams may not work under the constraint of symmetric strategies. We then adopt the common information approach for our problem and modify it to accommodate the use of symmetric strategies. This results in a common information based dynamic program where each step involves minimization over a single function from the space of an agent's private information to the space of probability distributions over actions. We present specialized models where private information can be reduced using simple dynamic program based arguments., Comment: Accepted at CDC 2023

Recent research has examined the possibility of using robots to guide evacuees to safe exits during emergencies. Yet, there are many factors that can impact a person's decision to follow a robot. Being able to model how an evacuee follows an emergency robot guide could be crucial for designing robots that effectively guide evacuees during an emergency. This paper presents a method for developing realistic and predictive human evacuee models from physical human evacuation experiments. The paper analyzes the behavior of 14 human subjects during physical robot-guided evacuation. We then use the video data to create evacuee motion models that predict the person's future positions during the emergency. Finally, we validate the resulting models by running a k-fold cross-validation on the data collected during physical human subject experiments. We also present performance results of the model using data from a similar simulated emergency evacuation experiment demonstrating that these models can serve as a tool to predict evacuee behavior in novel evacuation simulations.