The University of Michigan Robotics program focuses on the study of embodied intelligence that must sense, reason, act, and work with people to improve quality of life and productivity equitably across society. ROB 204, part of the core curriculum towards the undergraduate degree in Robotics, introduces students to topics that enable conceptually designing a robotic system to address users' needs from a sociotechnical context. Students are introduced to human-robot interaction (HRI) concepts and the process for socially-engaged design with a Learn-Reinforce-Integrate approach. In this paper, we discuss the course topics and our teaching methodology, and provide recommendations for delivering this material. Overall, students leave the course with a new understanding and appreciation for how human capabilities can inform requirements for a robotics system, how humans can interact with a robot, and how to assess the usability of robotic systems.

Complex planning and scheduling problems have long been solved using various optimization or heuristic approaches. In recent years, imitation learning that aims to learn from expert demonstrations has been proposed as a viable alternative to solving these problems. Generally speaking, imitation learning is designed to learn either the reward (or preference) model or directly the behavioral policy by observing the behavior of an expert. Existing work in imitation learning and inverse reinforcement learning has focused on imitation primarily in unconstrained settings (e.g., no limit on fuel consumed by the vehicle). However, in many real-world domains, the behavior of an expert is governed not only by reward (or preference) but also by constraints. For instance, decisions on self-driving delivery vehicles are dependent not only on the route preferences/rewards (depending on past demand data) but also on the fuel in the vehicle and the time available. In such problems, imitation learning is challenging as decisions are not only dictated by the reward model but are also dependent on a cost-constrained model. In this paper, we provide multiple methods that match expert distributions in the presence of trajectory cost constraints through (a) Lagrangian-based method; (b) Meta-gradients to find a good trade-off between expected return and minimizing constraint violation; and (c) Cost-violation-based alternating gradient. We empirically show that leading imitation learning approaches imitate cost-constrained behaviors poorly and our meta-gradient-based approach achieves the best performance.

Machine-learned language models have transformed everyday life: they steer us when we study, drive, manage money. They have the potential to transform our civilization. But they hallucinate. Their realities are virtual. This note provides a high-level overview of language models and outlines a low-level model of learning machines. It turns out that, after they become capable of recognizing hallucinations and dreaming safely, as humans tend to be, the language-learning machines proceed to generate broader systems of false beliefs and self-confirming theories, as humans tend to do.

We focus on offline imitation learning (IL), which aims to mimic an expert's behavior using demonstrations without any interaction with the environment. One of the main challenges in offline IL is the limited support of expert demonstrations, which typically cover only a small fraction of the state-action space. While it may not be feasible to obtain numerous expert demonstrations, it is often possible to gather a larger set of sub-optimal demonstrations. For example, in treatment optimization problems, there are varying levels of doctor treatments available for different chronic conditions. These range from treatment specialists and experienced general practitioners to less experienced general practitioners. Similarly, when robots are trained to imitate humans in routine tasks, they might learn from individuals with different levels of expertise and efficiency. In this paper, we propose an offline IL approach that leverages the larger set of sub-optimal demonstrations while effectively mimicking expert trajectories. Existing offline IL methods based on behavior cloning or distribution matching often face issues such as overfitting to the limited set of expert demonstrations or inadvertently imitating sub-optimal trajectories from the larger dataset. Our approach, which is based on inverse soft-Q learning, learns from both expert and sub-optimal demonstrations. It assigns higher importance (through learned weights) to aligning with expert demonstrations and lower importance to aligning with sub-optimal ones. A key contribution of our approach, called SPRINQL, is transforming the offline IL problem into a convex optimization over the space of Q functions. Through comprehensive experimental evaluations, we demonstrate that the SPRINQL algorithm achieves state-of-the-art (SOTA) performance on offline IL benchmarks. Code is available at https://github.com/hmhuy2000/SPRINQL.

Direct Preference Optimization (DPO) has recently emerged as a popular approach to improve reinforcement learning with human feedback (RLHF), leading to better techniques to fine-tune large language models (LLM). A weakness of DPO, however, lies in its lack of capability to characterize the diversity of human preferences. Inspired by Mallows' theory of preference ranking, we develop in this paper a new approach, the Mallows-DPO. A distinct feature of this approach is a dispersion index, which reflects the dispersion of human preference to prompts. We show that existing DPO models can be reduced to special cases of this dispersion index, thus unified with Mallows-DPO. More importantly, we demonstrate (empirically) how to use this dispersion index to enhance the performance of DPO in a broad array of benchmark tasks, from synthetic bandit selection to controllable generations and dialogues, while maintaining great generalization capabilities.

Thermal management of power electronics and Electronic Control Units is crucial in times of increasing power densities and limited assembly space. Electric and autonomous vehicles are a prominent application field. Thermal Interface Materials are used to transfer heat from a semiconductor to a heatsink. They are applied along a dispense path onto the semiconductor and spread over its entire surface once the heatsink is joined. To plan this application path, design engineers typically perform an iterative trial-and-error procedure of elaborate simulations and manual experiments. We propose a fully automated optimization approach, which clearly outperforms the current manual path planning and respects all relevant manufacturing constraints. An optimum dispense path increases the reliability of the thermal interface and makes the manufacturing more sustainable by reducing material waste. We show results on multiple real products from automotive series production, including an experimental validation on actual series manufacturing equipment.

We generalize active learning to address real-world settings with concrete prediction targets where sampling is restricted to an accessible region of the domain, while prediction targets may lie outside this region. We analyze a family of decision rules that sample adaptively to minimize uncertainty about prediction targets. We are the first to show, under general regularity assumptions, that such decision rules converge uniformly to the smallest possible uncertainty obtainable from the accessible data. We demonstrate their strong sample efficiency in two key applications: Active few-shot fine-tuning of large neural networks and safe Bayesian optimization, where they improve significantly upon the state-of-the-art.

Next-generation (xG) wireless networks, with their complex and dynamic nature, present significant challenges to using traditional optimization techniques. Generative AI (GAI) emerges as a powerful tool due to its unique strengths. Unlike traditional optimization techniques and other machine learning methods, GAI excels at learning from real-world network data, capturing its intricacies. This enables safe, offline exploration of various configurations and generation of diverse, unseen scenarios, empowering proactive, data-driven exploration and optimization for xG networks. Additionally, GAI's scalability makes it ideal for large-scale xG networks. This paper surveys how GAI-based models unlock optimization opportunities in xG wireless networks. We begin by providing a review of GAI models and some of the major communication paradigms of xG (e.g., 6G) wireless networks. We then delve into exploring how GAI can be used to improve resource allocation and enhance overall network performance. Additionally, we briefly review the networking requirements for supporting GAI applications in xG wireless networks. The paper further discusses the key challenges and future research directions in leveraging GAI for network optimization. Finally, a case study demonstrates the application of a diffusion-based GAI model for load balancing, carrier aggregation, and backhauling optimization in non-terrestrial networks, a core technology of xG networks. This case study serves as a practical example of how the combination of reinforcement learning and GAI can be implemented to address real-world network optimization problems.

Recent large language models (LLMs) have witnessed significant advancement in various tasks, including mathematical reasoning and theorem proving. As these two tasks require strict and formal multi-step inference, they are appealing domains for exploring the reasoning ability of LLMs but still face important challenges. Previous studies such as Chain-of-Thought (CoT) have revealed the effectiveness of intermediate steps guidance. However, such step-wise annotation requires heavy labor, leading to insufficient training steps for current benchmarks. To fill this gap, this work introduces MUSTARD, a data generation framework that masters uniform synthesis of theorem and proof data of high quality and diversity. MUSTARD synthesizes data in three stages: (1) It samples a few mathematical concept seeds as the problem category. (2) Then, it prompts a generative language model with the sampled concepts to obtain both the problems and their step-wise formal solutions. (3) Lastly, the framework utilizes a proof assistant (e.g., Lean Prover) to filter the valid proofs. With the proposed MUSTARD, we present a theorem-and-proof benchmark MUSTARDSAUCE with 5,866 valid data points. Each data point contains an informal statement, an informal proof, and a translated formal proof that passes the prover validation. We perform extensive analysis and demonstrate that MUSTARD generates validated high-quality step-by-step data. We further apply the MUSTARDSAUCE for fine-tuning smaller language models. The fine-tuned Llama 2-7B achieves a 15.41% average relative performance gain in automated theorem proving, and 8.18% in math word problems. Codes and data are available at https://github.com/Eleanor-H/MUSTARD.

In recent years, with the development of quantum machine learning, quantum neural networks (QNNs) have gained increasing attention in the field of natural language processing (NLP) and have achieved a series of promising results. However, most existing QNN models focus on the architectures of quantum recurrent neural network (QRNN) and self-attention mechanism (QSAM). In this work, we propose a novel QNN model based on quantum convolution. We develop the quantum depthwise convolution that significantly reduces the number of parameters and lowers computational complexity. We also introduce the multi-scale feature fusion mechanism to enhance model performance by integrating word-level and sentence-level features. Additionally, we propose the quantum word embedding and quantum sentence embedding, which provide embedding vectors more efficiently. Through experiments on two benchmark text classification datasets, we demonstrate our model outperforms a wide range of state-of-the-art QNN models. Notably, our model achieves a new state-of-the-art test accuracy of 96.77% on the RP dataset. We also show the advantages of our quantum model over its classical counterparts in its ability to improve test accuracy using fewer parameters. Finally, an ablation test confirms the effectiveness of the multi-scale feature fusion mechanism and quantum depthwise convolution in enhancing model performance.