Search

This paper examines the impact, characteristics, and entrepreneurial proclivities of foreign-born college graduates in the United States. A significant body of research has found that immigrants are more likely to start businesses than those born in the U.S., and the propensity of international students to concentrate in STEM fields indicates enormous potential for economic contributions and innovation. Yet the static nature of the immigration system, with visa pathways and restrictions that discourage business creation, hamper the nation's ability to take full advantage of the benefits immigrants can provide. In fact, this study finds that the U.S. immigration system likely delays foreign-born graduates from creating incorporated firms by as many as five years. The authors estimate that the creation of 150,000 incorporated firms and 580,000 jobs were delayed between 2013 and 2021. Without reform, the U.S. will continue to depress high-value firm creation by international students and cease to be the primary destination of global talent.

This work introduces Hierarchical Preference Optimization (HPO), a novel approach to hierarchical reinforcement learning (HRL) that addresses non-stationarity and infeasible subgoal generation issues when solving complex robotic control tasks. HPO leverages maximum entropy reinforcement learning combined with token-level Direct Preference Optimization (DPO), eliminating the need for pre-trained reference policies that are typically unavailable in challenging robotic scenarios. Mathematically, we formulate HRL as a bi-level optimization problem and transform it into a primitive-regularized DPO formulation, ensuring feasible subgoal generation and avoiding degenerate solutions. Extensive experiments on challenging robotic navigation and manipulation tasks demonstrate impressive performance of HPO, where it shows an improvement of up to 35% over the baselines. Furthermore, ablation studies validate our design choices, and quantitative analyses confirm the ability of HPO to mitigate non-stationarity and infeasible subgoal generation issues in HRL.

Embodied Question Answering (EQA) is an essential yet challenging task for robotic home assistants. Recent studies have shown that large vision-language models (VLMs) can be effectively utilized for EQA, but existing works either focus on video-based question answering without embodied exploration or rely on closed-form choice sets. In real-world scenarios, a robotic agent must efficiently explore and accurately answer questions in open-vocabulary settings. To address these challenges, we propose a novel framework called EfficientEQA for open-vocabulary EQA, which enables efficient exploration and accurate answering. In EfficientEQA, the robot actively explores unknown environments using Semantic-Value-Weighted Frontier Exploration, a strategy that prioritizes exploration based on semantic importance provided by calibrated confidence from black-box VLMs to quickly gather relevant information. To generate accurate answers, we employ Retrieval-Augmented Generation (RAG), which utilizes BLIP to retrieve useful images from accumulated observations and VLM reasoning to produce responses without relying on predefined answer choices. Additionally, we detect observations that are highly relevant to the question as outliers, allowing the robot to determine when it has sufficient information to stop exploring and provide an answer. Experimental results demonstrate the effectiveness of our approach, showing an improvement in answering accuracy by over 15% and efficiency, measured in running steps, by over 20% compared to state-of-the-art methods.

Data selection is crucial for optimizing language model (LM) performance on specific tasks, yet most existing methods fail to effectively consider the target task distribution. Current approaches either ignore task-specific requirements entirely or rely on approximations that fail to capture the nuanced patterns needed for tasks like Autoformalization or code generation. Methods that do consider the target distribution often rely on simplistic, sometimes noisy, representations, like hashed n-gram features, which can lead to collisions and introduce noise. We introduce ZIP-FIT, a data selection framework that uses gzip compression to directly measure alignment between potential training data and the target task distribution. In extensive evaluations on Autoformalization and Python code generation, ZIP-FIT significantly outperforms leading baselines like DSIR and D4. Models trained on ZIP-FIT-selected data achieve their lowest cross-entropy loss up to 85.1\% faster than baselines, demonstrating that better task alignment leads to more efficient learning. In addition, ZIP-FIT performs selection up to 65.8\% faster than DSIR and two orders of magnitude faster than D4. Notably, ZIP-FIT shows that smaller, well-aligned datasets often outperform larger but less targeted ones, demonstrating that a small amount of higher quality data is superior to a large amount of lower quality data. Our results imply that task-aware data selection is crucial for efficient domain adaptation, and that compression offers a principled way to measure task alignment. By showing that targeted data selection can dramatically improve task-specific performance, our work provides new insights into the relationship between data quality, task alignment, and model learning efficiency.

The importance of Reinforcement Learning from Human Feedback (RLHF) in aligning large language models (LLMs) with human values cannot be overstated. RLHF is a three-stage process that includes supervised fine-tuning (SFT), reward learning, and policy learning. Although there are several offline and online approaches to aligning LLMs, they often suffer from distribution shift issues. These issues arise from the inability to accurately capture the distributional interdependence between the reward learning and policy learning stages. Consequently, this has led to various approximated approaches, but the theoretical insights and motivations remain largely limited to tabular settings, which do not hold in practice. This gap between theoretical insights and practical implementations is critical. It is challenging to address this gap as it requires analyzing the performance of AI alignment algorithms in neural network-parameterized settings. Although bi-level formulations have shown promise in addressing distribution shift issues, they suffer from the hyper-gradient problem, and current approaches lack efficient algorithms to solve this. In this work, we tackle these challenges employing the bi-level formulation laid out in Kwon et al. (2024) along with the assumption \emph{Weak Gradient Domination} to demonstrate convergence in an RLHF setup, obtaining a sample complexity of $\epsilon^{-\frac{7}{2}}$ . Our key contributions are twofold: (i) We propose a bi-level formulation for AI alignment in parameterized settings and introduce a first-order approach to solve this problem. (ii) We analyze the theoretical convergence rates of the proposed algorithm and derive state-of-the-art bounds. To the best of our knowledge, this is the first work to establish convergence rate bounds and global optimality for the RLHF framework in neural network-parameterized settings.

A substantial amount of variability in ECG manifested due to patient characteristics hinders the adoption of automated analysis algorithms in clinical practice. None of the ECG annotators developed till date consider the characteristics of the patients in a multi-modal architecture. We employed the XGBoost model to analyze the UCI Arrhythmia dataset, linking patient characteristics to ECG morphological changes. The model accurately classified patient gender using discriminative ECG features with 87.75% confidence. We propose a novel multi-modal methodology for ECG analysis and arrhythmia classification that can help defy the variability in ECG related to patient-specific conditions. This deep learning algorithm, named rECGnition_v1.0 (robust ECG abnormality detection Version 1), fuses Beat Morphology with Patient Characteristics to create a discriminative feature map that understands the internal correlation between both modalities. A Squeeze and Excitation based Patient characteristic Encoding Network (SEPcEnet) has been introduced, considering the patient's demographics. The trained model outperformed the various existing algorithms by achieving the overall F1-score of 0.986 for the ten arrhythmia class classification in the MITDB and achieved near perfect prediction scores of ~0.99 for LBBB, RBBB, Premature ventricular contraction beat, Atrial premature beat and Paced beat. Subsequently, the methodology was validated across INCARTDB, EDB and different class groups of MITDB using transfer learning. The generalizability test provided F1-scores of 0.980, 0.946, 0.977, and 0.980 for INCARTDB, EDB, MITDB AAMI, and MITDB Normal vs. Abnormal Classification, respectively. Therefore, with a more enhanced and comprehensive understanding of the patient being examined and their ECG for diverse CVD manifestations, the proposed rECGnition_v1.0 algorithm paves the way for its deployment in clinics.

Reinforcement learning with general utilities has recently gained attention thanks to its ability to unify several problems, including imitation learning, pure exploration, and safe RL. However, prior work for solving this general problem in a unified way has mainly focused on the tabular setting. This is restrictive when considering larger state-action spaces because of the need to estimate occupancy measures during policy optimization. In this work, we address this issue and propose to approximate occupancy measures within a function approximation class using maximum likelihood estimation (MLE). We propose a simple policy gradient algorithm (PG-OMA) where an actor updates the policy parameters to maximize the general utility objective whereas a critic approximates the occupancy measure using MLE. We provide a sample complexity analysis of PG-OMA showing that our occupancy measure estimation error only scales with the dimension of our function approximation class rather than the size of the state action space. Under suitable assumptions, we establish first order stationarity and global optimality performance bounds for the proposed PG-OMA algorithm for nonconcave and concave general utilities respectively. We complement our methodological and theoretical findings with promising empirical results showing the scalability potential of our approach compared to existing tabular count-based approaches., Comment: 26 pages, 5 figures

Text-based AI system optimization typically involves a feedback loop scheme where a single LLM generates an evaluation in natural language of the current output to improve the next iteration's output. However, in this work, we empirically demonstrate that for a practical and complex task (code generation) with multiple criteria to evaluate, utilizing only one LLM evaluator tends to let errors in generated code go undetected, thus leading to incorrect evaluations and ultimately suboptimal test case performance. Motivated by this failure case, we assume there exists an optimal evaluation policy that samples an evaluation between response and ground truth. We then theoretically prove that a linear combination of multiple evaluators can approximate this optimal policy. From this insight, we propose AI system optimization via Multiple LLM Evaluators (AIME). AIME is an evaluation protocol that utilizes multiple LLMs that each independently generate an evaluation on separate criteria and then combine them via concatenation. We provide an extensive empirical study showing AIME outperforming baseline methods in code generation tasks, with up to $62\%$ higher error detection rate and up to $16\%$ higher success rate than a single LLM evaluation protocol on LeetCodeHard and HumanEval datasets. We also show that the selection of the number of evaluators and which criteria to utilize is non-trivial as it can impact pact success rate by up to $12\%$., Comment: 21 pages, 10 Figures, 4 Tables

In an era of "moving fast and breaking things", regulators have moved slowly to pick up the safety, bias, and legal pieces left in the wake of broken Artificial Intelligence (AI) deployment. Since AI models, such as large language models, are able to push misinformation and stoke division within our society, it is imperative for regulators to employ a framework that mitigates these dangers and ensures user safety. While there is much-warranted discussion about how to address the safety, bias, and legal woes of state-of-the-art AI models, the number of rigorous and realistic mathematical frameworks to regulate AI safety is lacking. We take on this challenge, proposing an auction-based regulatory mechanism that provably incentivizes model-building agents (i) to deploy safer models and (ii) to participate in the regulation process. We provably guarantee, via derived Nash Equilibria, that each participating agent's best strategy is to submit a model safer than a prescribed minimum-safety threshold. Empirical results show that our regulatory auction boosts safety and participation rates by 20% and 15% respectively, outperforming simple regulatory frameworks that merely enforce minimum safety standards., Comment: 20 pages, 7 figures

The growing demand for machine learning in healthcare requires processing increasingly large electronic health record (EHR) datasets, but existing pipelines are not computationally efficient or scalable. In this paper, we introduce meds_reader, an optimized Python package for efficient EHR data processing that is designed to take advantage of many intrinsic properties of EHR data for improved speed. We then demonstrate the benefits of meds_reader by reimplementing key components of two major EHR processing pipelines, achieving 10-100x improvements in memory, speed, and disk usage. The code for meds_reader can be found at https://github.com/som-shahlab/meds_reader.

We propose a solution to the strong CP problem that specifically relies on massless quarks and has no light axion. The QCD color group $SU(3)_c$ is embedded into a larger, simple gauge group (grand-color) where one of the massless, colored fermions enjoys an anomalous chiral symmetry, rendering the strong CP phase unphysical. The grand-color gauge group $G_{\rm GC}$ is Higgsed down to $SU(3)_c\times G_{c'}$, after which $G_{c'}$ eventually confines at a lower scale, spontaneously breaking the chiral symmetry and generating a real, positive mass to the massless, colored fermion. Since the chiral symmetry has a $G_{c'}$ anomaly, there is no corresponding light Nambu-Goldstone boson. The anomalous chiral symmetry can be an accidental symmetry that arises from an exact discrete symmetry without introducing a domain wall problem. Potential experimental signals of our mechanism include vector-like quarks near the TeV scale, pseudo Nambu-Goldstone bosons below the 10 GeV scale, light dark matter decay, and primordial gravitational waves from the new strong dynamics., Comment: 62 pages, 12 figures

Transfer learning in reinforcement learning (RL) has become a pivotal strategy for improving data efficiency in new, unseen tasks by utilizing knowledge from previously learned tasks. This approach is especially beneficial in real-world deployment scenarios where computational resources are constrained and agents must adapt rapidly to novel environments. However, current state-of-the-art methods often fall short in ensuring safety during the transfer process, particularly when unforeseen risks emerge in the deployment phase. In this work, we address these limitations by introducing a novel Caution-Aware Transfer Learning (CAT) framework. Unlike traditional approaches that limit risk considerations to mean-variance, we define "caution" as a more generalized and comprehensive notion of risk. Our core innovation lies in optimizing a weighted sum of reward return and caution-based on state-action occupancy measures-during the transfer process, allowing for a rich representation of diverse risk factors. To the best of our knowledge, this is the first work to explore the optimization of such a generalized risk notion within the context of transfer RL. Our contributions are threefold: (1) We propose a Caution-Aware Transfer (CAT) framework that evaluates source policies within the test environment and constructs a new policy that balances reward maximization and caution. (2) We derive theoretical sub-optimality bounds for our method, providing rigorous guarantees of its efficacy. (3) We empirically validate CAT, demonstrating that it consistently outperforms existing methods by delivering safer policies under varying risk conditions in the test tasks.

While LLMs are proficient at processing text in human conversations, they often encounter difficulties with the nuances of verbal instructions and, thus, remain prone to hallucinate trust in human command. In this work, we present TrustNavGPT, an LLM based audio guided navigation agent that uses affective cues in spoken communication elements such as tone and inflection that convey meaning beyond words, allowing it to assess the trustworthiness of human commands and make effective, safe decisions. Our approach provides a lightweight yet effective approach that extends existing LLMs to model audio vocal features embedded in the voice command and model uncertainty for safe robotic navigation.

Reinforcement Learning from Human Feedback (RLHF) is a key method for aligning large language models (LLMs) with human preferences. However, current offline alignment approaches like DPO, IPO, and SLiC rely heavily on fixed preference datasets, which can lead to sub-optimal performance. On the other hand, recent literature has focused on designing online RLHF methods but still lacks a unified conceptual formulation and suffers from distribution shift issues. To address this, we establish that online LLM alignment is underpinned by bilevel optimization. By reducing this formulation to an efficient single-level first-order method (using the reward-policy equivalence), our approach generates new samples and iteratively refines model alignment by exploring responses and regulating preference labels. In doing so, we permit alignment methods to operate in an online and self-improving manner, as well as generalize prior online RLHF methods as special cases. Compared to state-of-the-art iterative RLHF methods, our approach significantly improves alignment performance on open-sourced datasets with minimal computational overhead., Comment: 24 pages, 6 figures, 3 tables

Large language models (LLMs) have grown in popularity due to their natural language interface and pre trained knowledge, leading to rapidly increasing success in question-answering (QA) tasks. More recently, multi-agent systems with LLM-based agents (Multi-LLM) have been utilized increasingly more for QA. In these scenarios, the models may each answer the question and reach a consensus or each model is specialized to answer different domain questions. However, most prior work dealing with Multi-LLM QA has focused on scenarios where the models are asked in a zero-shot manner or are given information sources to extract the answer. For question answering of an unknown environment, embodied exploration of the environment is first needed to answer the question. This skill is necessary for personalizing embodied AI to environments such as households. There is a lack of insight into whether a Multi-LLM system can handle question-answering based on observations from embodied exploration. In this work, we address this gap by investigating the use of Multi-Embodied LLM Explorers (MELE) for QA in an unknown environment. Multiple LLM-based agents independently explore and then answer queries about a household environment. We analyze different aggregation methods to generate a single, final answer for each query: debating, majority voting, and training a central answer module (CAM). Using CAM, we observe a $46\%$ higher accuracy compared against the other non-learning-based aggregation methods. We provide code and the query dataset for further research., Comment: 16 pages, 9 Figures, 5 Tables

Learning control policies to perform complex robotics tasks from human preference data presents significant challenges. On the one hand, the complexity of such tasks typically requires learning policies to perform a variety of subtasks, then combining them to achieve the overall goal. At the same time, comprehensive, well-engineered reward functions are typically unavailable in such problems, while limited human preference data often is; making efficient use of such data to guide learning is therefore essential. Methods for learning to perform complex robotics tasks from human preference data must overcome both these challenges simultaneously. In this work, we introduce DIPPER: Direct Preference Optimization to Accelerate Primitive-Enabled Hierarchical Reinforcement Learning, an efficient hierarchical approach that leverages direct preference optimization to learn a higher-level policy and reinforcement learning to learn a lower-level policy. DIPPER enjoys improved computational efficiency due to its use of direct preference optimization instead of standard preference-based approaches such as reinforcement learning from human feedback, while it also mitigates the well-known hierarchical reinforcement learning issues of non-stationarity and infeasible subgoal generation due to our use of primitive-informed regularization inspired by a novel bi-level optimization formulation of the hierarchical reinforcement learning problem. To validate our approach, we perform extensive experimental analysis on a variety of challenging robotics tasks, demonstrating that DIPPER outperforms hierarchical and non-hierarchical baselines, while ameliorating the non-stationarity and infeasible subgoal generation issues of hierarchical reinforcement learning.

Aligning foundation models is essential for their safe and trustworthy deployment. However, traditional fine-tuning methods are computationally intensive and require updating billions of model parameters. A promising alternative, alignment via decoding, adjusts the response distribution directly without model updates to maximize a target reward $r$, thus providing a lightweight and adaptable framework for alignment. However, principled decoding methods rely on oracle access to an optimal Q-function ($Q^*$), which is often unavailable in practice. Hence, prior SoTA methods either approximate this $Q^*$ using $Q^{\pi_{\texttt{sft}}}$ (derived from the reference $\texttt{SFT}$ model) or rely on short-term rewards, resulting in sub-optimal decoding performance. In this work, we propose Transfer $Q^*$, which implicitly estimates the optimal value function for a target reward $r$ through a baseline model $\rho_{\texttt{BL}}$ aligned with a baseline reward $\rho_{\texttt{BL}}$ (which can be different from the target reward $r$). Theoretical analyses of Transfer $Q^*$ provide a rigorous characterization of its optimality, deriving an upper bound on the sub-optimality gap and identifying a hyperparameter to control the deviation from the pre-trained reference $\texttt{SFT}$ model based on user needs. Our approach significantly reduces the sub-optimality gap observed in prior SoTA methods and demonstrates superior empirical performance across key metrics such as coherence, diversity, and quality in extensive tests on several synthetic and real datasets.

Standard federated learning (FL) approaches are vulnerable to the free-rider dilemma: participating agents can contribute little to nothing yet receive a well-trained aggregated model. While prior mechanisms attempt to solve the free-rider dilemma, none have addressed the issue of truthfulness. In practice, adversarial agents can provide false information to the server in order to cheat its way out of contributing to federated training. In an effort to make free-riding-averse federated mechanisms truthful, and consequently less prone to breaking down in practice, we propose FACT. FACT is the first federated mechanism that: (1) eliminates federated free riding by using a penalty system, (2) ensures agents provide truthful information by creating a competitive environment, and (3) encourages agent participation by offering better performance than training alone. Empirically, FACT avoids free-riding when agents are untruthful, and reduces agent loss by over 4x., Comment: NeurIPS 2024, 19 pages, 7 figures

The current state-of-the-art theoretical analysis of Actor-Critic (AC) algorithms significantly lags in addressing the practical aspects of AC implementations. This crucial gap needs bridging to bring the analysis in line with practical implementations of AC. To address this, we advocate for considering the MMCLG criteria: \textbf{M}ulti-layer neural network parametrization for actor/critic, \textbf{M}arkovian sampling, \textbf{C}ontinuous state-action spaces, the performance of the \textbf{L}ast iterate, and \textbf{G}lobal optimality. These aspects are practically significant and have been largely overlooked in existing theoretical analyses of AC algorithms. In this work, we address these gaps by providing the first comprehensive theoretical analysis of AC algorithms that encompasses all five crucial practical aspects (covers MMCLG criteria). We establish global convergence sample complexity bounds of $\tilde{\mathcal{O}}\left({\epsilon^{-3}}\right)$. We achieve this result through our novel use of the weak gradient domination property of MDP's and our unique analysis of the error in critic estimation., Comment: Accepted at ICML 2024. This is a revised version of arXiv:2306.10486, where we have gone from finite action space to continuous action space, from average iterate convergence to last iterate convergence and from $\epsilon^{-4}$ to $\epsilon^{-3}$ sample complexity

In this work, we introduce PIPER: Primitive-Informed Preference-based Hierarchical reinforcement learning via Hindsight Relabeling, a novel approach that leverages preference-based learning to learn a reward model, and subsequently uses this reward model to relabel higher-level replay buffers. Since this reward is unaffected by lower primitive behavior, our relabeling-based approach is able to mitigate non-stationarity, which is common in existing hierarchical approaches, and demonstrates impressive performance across a range of challenging sparse-reward tasks. Since obtaining human feedback is typically impractical, we propose to replace the human-in-the-loop approach with our primitive-in-the-loop approach, which generates feedback using sparse rewards provided by the environment. Moreover, in order to prevent infeasible subgoal prediction and avoid degenerate solutions, we propose primitive-informed regularization that conditions higher-level policies to generate feasible subgoals for lower-level policies. We perform extensive experiments to show that PIPER mitigates non-stationarity in hierarchical reinforcement learning and achieves greater than 50$\%$ success rates in challenging, sparse-reward robotic environments, where most other baselines fail to achieve any significant progress.

The human body consists of microbiomes associated with the development and prevention of several diseases. These microbial organisms form several complex interactions that are informative to the scientific community for explaining disease progression and prevention. Contrary to the traditional view of the microbiome as a singular, assortative network, we introduce a novel statistical approach using a weighted stochastic infinite block model to analyze the complex community structures within microbial co-occurrence microbial interaction networks. Our model defines connections between microbial taxa using a novel semi-parametric rank-based correlation method on their transformed relative abundances within a fully connected network framework. Employing a Bayesian nonparametric approach, the proposed model effectively clusters taxa into distinct communities while estimating the number of communities. The posterior summary of the taxa community membership is obtained based on the posterior probability matrix, which could naturally solve the label switching problem. Through simulation studies and real-world application to microbiome data from postmenopausal patients with recurrent urinary tract infections, we demonstrate that our method has superior clustering accuracy over alternative approaches. This advancement provides a more nuanced understanding of microbiome organization, with significant implications for disease research., Comment: 25 pages

In the context of average-reward reinforcement learning, the requirement for oracle knowledge of the mixing time, a measure of the duration a Markov chain under a fixed policy needs to achieve its stationary distribution, poses a significant challenge for the global convergence of policy gradient methods. This requirement is particularly problematic due to the difficulty and expense of estimating mixing time in environments with large state spaces, leading to the necessity of impractically long trajectories for effective gradient estimation in practical applications. To address this limitation, we consider the Multi-level Actor-Critic (MAC) framework, which incorporates a Multi-level Monte-Carlo (MLMC) gradient estimator. With our approach, we effectively alleviate the dependency on mixing time knowledge, a first for average-reward MDPs global convergence. Furthermore, our approach exhibits the tightest available dependence of $\mathcal{O}\left( \sqrt{\tau_{mix}} \right)$known from prior work. With a 2D grid world goal-reaching navigation experiment, we demonstrate that MAC outperforms the existing state-of-the-art policy gradient-based method for average reward settings., Comment: 26 Pages, 2 Figures

We present a novel approach to tackle the ObjectNav task for non-stationary and potentially occluded targets in an indoor environment. We refer to this task Portable ObjectNav (or P-ObjectNav), and in this work, present its formulation, feasibility, and a navigation benchmark using a novel memory-enhanced LLM-based policy. In contrast to ObjNav where target object locations are fixed for each episode, P-ObjectNav tackles the challenging case where the target objects move during the episode. This adds a layer of time-sensitivity to navigation, and is particularly relevant in scenarios where the agent needs to find portable targets (e.g. misplaced wallets) in human-centric environments. The agent needs to estimate not just the correct location of the target, but also the time at which the target is at that location for visual grounding -- raising the question about the feasibility of the task. We address this concern by inferring results on two cases for object placement: one where the objects placed follow a routine or a path, and the other where they are placed at random. We dynamize Matterport3D for these experiments, and modify PPO and LLM-based navigation policies for evaluation. Using PPO, we observe that agent performance in the random case stagnates, while the agent in the routine-following environment continues to improve, allowing us to infer that P-ObjectNav is solvable in environments with routine-following object placement. Using memory-enhancement on an LLM-based policy, we set a benchmark for P-ObjectNav. Our memory-enhanced agent significantly outperforms their non-memory-based counterparts across object placement scenarios by 71.76% and 74.68% on average when measured by Success Rate (SR) and Success Rate weighted by Path Length (SRPL), showing the influence of memory on improving P-ObjectNav performance. Our code and dataset will be made publicly available., Comment: 32

Multi-Agent Reinforcement Learning (MARL) algorithms face the challenge of efficient exploration due to the exponential increase in the size of the joint state-action space. While demonstration-guided learning has proven beneficial in single-agent settings, its direct applicability to MARL is hindered by the practical difficulty of obtaining joint expert demonstrations. In this work, we introduce a novel concept of personalized expert demonstrations, tailored for each individual agent or, more broadly, each individual type of agent within a heterogeneous team. These demonstrations solely pertain to single-agent behaviors and how each agent can achieve personal goals without encompassing any cooperative elements, thus naively imitating them will not achieve cooperation due to potential conflicts. To this end, we propose an approach that selectively utilizes personalized expert demonstrations as guidance and allows agents to learn to cooperate, namely personalized expert-guided MARL (PegMARL). This algorithm utilizes two discriminators: the first provides incentives based on the alignment of policy behavior with demonstrations, and the second regulates incentives based on whether the behavior leads to the desired objective. We evaluate PegMARL using personalized demonstrations in both discrete and continuous environments. The results demonstrate that PegMARL learns near-optimal policies even when provided with suboptimal demonstrations, and outperforms state-of-the-art MARL algorithms in solving coordinated tasks. We also showcase PegMARL's capability to leverage joint demonstrations in the StarCraft scenario and converge effectively even with demonstrations from non-co-trained policies.

In this paper, we highlight the critical issues of robustness and safety associated with integrating large language models (LLMs) and vision-language models (VLMs) into robotics applications. Recent works focus on using LLMs and VLMs to improve the performance of robotics tasks, such as manipulation and navigation. Despite these improvements, analyzing the safety of such systems remains underexplored yet extremely critical. LLMs and VLMs are highly susceptible to adversarial inputs, prompting a significant inquiry into the safety of robotic systems. This concern is important because robotics operate in the physical world where erroneous actions can result in severe consequences. This paper explores this issue thoroughly, presenting a mathematical formulation of potential attacks on LLM/VLM-based robotic systems and offering experimental evidence of the safety challenges. Our empirical findings highlight a significant vulnerability: simple modifications to the input can drastically reduce system effectiveness. Specifically, our results demonstrate an average performance deterioration of 19.4% under minor input prompt modifications and a more alarming 29.1% under slight perceptual changes. These findings underscore the urgent need for robust countermeasures to ensure the safe and reliable deployment of advanced LLM/VLM-based robotic systems.

Small instantons which increase the axion mass due to an appropriate modification of QCD at a UV scale $\Lambda_{\rm SI}$, can also enhance the effect of CP-violating operators to shift the axion potential minimum by an amount, $\theta_{\rm ind}$, proportional to the flavorful couplings in the SMEFT. Since physical observables must be flavor basis independent, we construct a basis of determinant-like flavor invariants that arise from instanton calculations containing the effects of dimension-six CP-odd operators at the scale $\require{cancel}\Lambda_{\cancel{\rm CP}}$. This new basis provides a more reliable estimate of the shift $\theta_{\rm ind}$, that is severely constrained by neutron electric dipole moment experiments. In particular, for the case of four-quark, semi-leptonic and gluon dipole operators, these invariants are then used to provide improved limits on the ratio of scales $\require{cancel}\Lambda_{\rm SI}/\Lambda_{\cancel{\rm CP}}$ for different flavor scenarios. The CP-odd flavor invariants also provide a classification of the leading effects from Wilson coefficients, and as an example, we show that a semi-leptonic four-fermion operator is subdominant compared to the four-quark operators. More generally, the flavor invariants, together with an instanton NDA, can be used to more accurately estimate small instanton effects in the axion potential that arise from any SMEFT operator., Comment: 49 pages, 4 figures; matches version published in JHEP

Reinforcement Learning from Human Feedback (RLHF) aligns language models to human preferences by employing a singular reward model derived from preference data. However, such an approach overlooks the rich diversity of human preferences inherent in data collected from multiple users. In this work, we first derive an impossibility result of alignment with single reward RLHF, thereby highlighting its insufficiency in representing diverse human preferences. To provide an equitable solution to the problem, we learn a mixture of preference distributions via an expectation-maximization algorithm and propose a MaxMin alignment objective for policy learning inspired by the Egalitarian principle in social choice theory to better represent diverse human preferences. We elucidate the connection of our proposed approach to distributionally robust optimization and general utility RL, thereby highlighting the generality and robustness of our proposed solution. We present comprehensive experimental results on small-scale (GPT-2) and large-scale language models (with Tulu2-7B) and show the efficacy of the proposed approach in the presence of diversity among human preferences. Our algorithm achieves an average improvement of more than 16% in win-rates over conventional RLHF algorithms and improves the win-rate (accuracy) for minority groups by over 33% without compromising the performance of majority groups, showcasing the robustness and fairness of our approach. We remark that our findings in this work are not only limited to language models but also extend to reinforcement learning in general.

While LLMs excel in processing text in these human conversations, they struggle with the nuances of verbal instructions in scenarios like social navigation, where ambiguity and uncertainty can erode trust in robotic and other AI systems. We can address this shortcoming by moving beyond text and additionally focusing on the paralinguistic features of these audio responses. These features are the aspects of spoken communication that do not involve the literal wording (lexical content) but convey meaning and nuance through how something is said. We present \emph{Beyond Text}; an approach that improves LLM decision-making by integrating audio transcription along with a subsection of these features, which focus on the affect and more relevant in human-robot conversations.This approach not only achieves a 70.26\% winning rate, outperforming existing LLMs by 22.16\% to 48.30\% (gemini-1.5-pro and gpt-3.5 respectively), but also enhances robustness against token manipulation adversarial attacks, highlighted by a 22.44\% less decrease ratio than the text-only language model in winning rate. ``\textit{Beyond Text}'' marks an advancement in social robot navigation and broader Human-Robot interactions, seamlessly integrating text-based guidance with human-audio-informed language models., Comment: 28 pages, 7 figures

The effectiveness of reinforcement learning (RL) agents in continuous control robotics tasks is heavily dependent on the design of the underlying reward function. However, a misalignment between the reward function and user intentions, values, or social norms can be catastrophic in the real world. Current methods to mitigate this misalignment work by learning reward functions from human preferences; however, they inadvertently introduce a risk of reward overoptimization. In this work, we address this challenge by advocating for the adoption of regularized reward functions that more accurately mirror the intended behaviors. We propose a novel concept of reward regularization within the robotic RLHF (RL from Human Feedback) framework, which we refer to as \emph{agent preferences}. Our approach uniquely incorporates not just human feedback in the form of preferences but also considers the preferences of the RL agent itself during the reward function learning process. This dual consideration significantly mitigates the issue of reward function overoptimization in RL. We provide a theoretical justification for the proposed approach by formulating the robotic RLHF problem as a bilevel optimization problem. We demonstrate the efficiency of our algorithm {\ours} in several continuous control benchmarks including DeepMind Control Suite \cite{tassa2018deepmind} and MetaWorld \cite{yu2021metaworld} and high dimensional visual environments, with an improvement of more than 70\% in sample efficiency in comparison to current SOTA baselines. This showcases our approach's effectiveness in aligning reward functions with true behavioral intentions, setting a new benchmark in the field.