In many domains of empirical sciences, discovering the causal structure within variables remains an indispensable task. Recently, to tackle with unoriented edges or latent assumptions violation suffered by conventional methods, researchers formulated a reinforcement learning (RL) procedure for causal discovery, and equipped REINFORCE algorithm to search for the best-rewarded directed acyclic graph. The two keys to the overall performance of the procedure are the robustness of RL methods and the efficient encoding of variables. However, on the one hand, REINFORCE is prone to local convergence and unstable performance during training. Neither trust region policy optimization, being computationally-expensive, nor proximal policy optimization (PPO), suffering from aggregate constraint deviation, is decent alternative for combinatory optimization problems with considerable individual subactions. We propose a trust region-navigated clipping policy optimization method for causal discovery that guarantees both better search efficiency and steadiness in policy optimization, in comparison with REINFORCE, PPO and our prioritized sampling-guided REINFORCE implementation. On the other hand, to boost the efficient encoding of variables, we propose a refined graph attention encoder called SDGAT that can grasp more feature information without priori neighbourhood information. With these improvements, the proposed method outperforms former RL method in both synthetic and benchmark datasets in terms of output results and optimization robustness.

Learning Human-A ware Robot Policies for Adaptive Assistance Jason Qin 1, Shikun Ban 2, Wentao Zhu 2, Yizhou Wang 2, and Dimitris Samaras 1 Abstract -- Developing robots that can assist humans efficiently, safely, and adaptively is crucial for real-world applications such as healthcare. While previous work often assumes a centralized system for co-optimizing human-robot interactions, we argue that real-world scenarios are much more complicated, as humans have individual preferences regarding how tasks are performed. However, to provide effective assistance, robots must still be able to recognize and adapt to the individual needs and preferences of different users. T o address these challenges, we propose a novel framework in which robots infer human intentions and reason about human utilities through interaction. Our approach features two critical modules: the anticipation module is a motion predictor that captures the spatial-temporal relationship between the robot agent and user agent, which contributes to predicting human behavior; the utility module infers the underlying human utility functions through progressive task demonstration sampling. Extensive experiments across various robot types and assistive tasks demonstrate that the proposed framework not only enhances task success and efficiency but also significantly improves user satisfaction, paving the way for more personalized and adaptive assistive robotic systems. Code and demos are available at https: //asonin.github.io/Human-Aware-Assistance/ . I. I NTRODUCTION Developing robots that understand and assist humans is a critical long-term goal in Artificial Intelligence (AI) research.

This work focuses on the mixed membership models for multivariate categorical data widely used for analyzing survey responses and population genetics data. These grade of membership (GoM) models offer rich modeling power but present significant estimation challenges for high-dimensional polytomous data. Popular existing approaches, such as Bayesian MCMC inference, are not scalable and lack theoretical guarantees in high-dimensional settings. To address this, we first observe that data from this model can be reformulated as a three-way (quasi-)tensor, with many subjects responding to many items with varying numbers of categories. We introduce a novel and simple approach that flattens the three-way quasi-tensor into a "fat" matrix, and then perform a singular value decomposition of it to estimate parameters by exploiting the singular subspace geometry. Our fast spectral method can accommodate a broad range of data distributions with arbitrarily locally dependent noise, which we formalize as the generalized-GoM models. We establish finite-sample entrywise error bounds for the generalized-GoM model parameters. This is supported by a new sharp two-to-infinity singular subspace perturbation theory for locally dependent and flexibly distributed noise, a contribution of independent interest. Simulations and applications to data in political surveys, population genetics, and single-cell sequencing demonstrate our method's superior performance.

Mean Field Control Games (MFCGs) provide a powerful theoretical framework for analyzing systems of infinitely many interacting agents, blending elements from Mean Field Games (MFGs) and Mean Field Control (MFC). However, solving the coupled Hamilton-Jacobi-Bellman and Fokker-Planck equations that characterize MFCG equilibria remains a significant computational challenge, particularly in high-dimensional or complex environments. This paper presents a scalable deep Reinforcement Learning (RL) approach to approximate equilibrium solutions of MFCGs. Building on previous works, We reformulate the infinite-agent stochastic control problem as a Markov Decision Process, where each representative agent interacts with the evolving mean field distribution. We use the actor-critic based algorithm from a previous paper (Angiuli et.al., 2024) as the baseline and propose several versions of more scalable and efficient algorithms, utilizing techniques including parallel sample collection (batching); mini-batching; target network; proximal policy optimization (PPO); generalized advantage estimation (GAE); and entropy regularization. By leveraging these techniques, we effectively improved the efficiency, scalability, and training stability of the baseline algorithm. We evaluate our method on a linear-quadratic benchmark problem, where an analytical solution to the MFCG equilibrium is available. Our results show that some versions of our proposed approach achieve faster convergence and closely approximate the theoretical optimum, outperforming the baseline algorithm by an order of magnitude in sample efficiency. Our work lays the foundation for adapting deep RL to solve more complicated MFCGs closely related to real life, such as large-scale autonomous transportation systems, multi-firm economic competition, and inter-bank borrowing problems.

Strong artificial intelligence (AI) is envisioned to possess general cognitive abilities and scientific creativity comparable to human intelligence, encompassing both knowledge acquisition and problem-solving. While remarkable progress has been made in weak AI, the realization of strong AI remains a topic of intense debate and critical examination. In this paper, we explore pivotal innovations in the history of astronomy and physics, focusing on the discovery of Neptune and the concept of scientific revolutions as perceived by philosophers of science. Building on these insights, we introduce a simple theoretical and statistical framework of weak beliefs, termed the Transformational Belief (TB) framework, designed as a foundation for modeling scientific creativity. Through selected illustrative examples in statistical science, we demonstrate the TB framework's potential as a promising foundation for understanding, analyzing, and even fostering creativity -- paving the way toward the development of strong AI. We conclude with reflections on future research directions and potential advancements.

The question of whether AI substitutes or complements human work is central to debates on the future of work. This paper examines the impact of AI on skill demand and compensation in the U.S. economy, analysing 12 million online job vacancies from 2018 to 2023. It investigates internal effects (within-job substitution and complementation) and external effects (across occupations, industries, and regions). Our findings reveal a significant increase in demand for AI-complementary skills, such as digital literacy, teamwork, and resilience, alongside rising wage premiums for these skills in AI roles like Data Scientist. Conversely, substitute skills, including customer service and text review, have declined in both demand and value within AI-related positions. Examining external effects, we find a notable rise in demand for complementary skills in non-AI roles linked to the growth of AI-related jobs in specific industries or regions. At the same time, there is a moderate decline in non-AI roles requiring substitute skills. Overall, AI's complementary effect is up to 50% larger than its substitution effect, resulting in net positive demand for skills. These results, replicated for the UK and Australia, highlight AI's transformative impact on workforce skill requirements. They suggest reskilling efforts should prioritise not only technical AI skills but also complementary skills like ethics and digital literacy.

This work focuses on building a task planner for Embodied Instruction Following (EIF) using Large Language Models (LLMs). Previous works typically train a planner to imitate expert trajectories, treating this as a supervised task. While these methods achieve competitive performance, they often lack sufficient robustness. When a suboptimal action is taken, the planner may encounter an out-of-distribution state, which can lead to task failure. In contrast, we frame the task as a Partially Observable Markov Decision Process (POMDP) and aim to develop a robust planner under a few-shot assumption. Thus, we propose a closed-loop planner with an adaptation module and a novel hindsight method, aiming to use as much information as possible to assist the planner. Our experiments on the ALFRED dataset indicate that our planner achieves competitive performance under a few-shot assumption. For the first time, our few-shot agent's performance approaches and even surpasses that of the full-shot supervised agent.

The Knowledge Tracing (KT) task focuses on predicting a learner's future performance based on the historical interactions. The knowledge state plays a key role in learning process. However, considering that the knowledge state is influenced by various learning factors in the interaction process, such as the exercises similarities, responses reliability and the learner's learning state. Previous models still face two major limitations. First, due to the exercises differences caused by various complex reasons and the unreliability of responses caused by guessing behavior, it is hard to locate the historical interaction which is most relevant to the current answered exercise. Second, the learning state is also a key factor to influence the knowledge state, which is always ignored by previous methods. To address these issues, we propose a new method named Learning State Enhanced Knowledge Tracing (LSKT). Firstly, to simulate the potential differences in interactions, inspired by Item Response Theory~(IRT) paradigm, we designed three different embedding methods ranging from coarse-grained to fine-grained views and conduct comparative analysis on them. Secondly, we design a learning state extraction module to capture the changing learning state during the learning process of the learner. In turn, with the help of the extracted learning state, a more detailed knowledge state could be captured. Experimental results on four real-world datasets show that our LSKT method outperforms the current state-of-the-art methods.

Local causal discovery aims to learn and distinguish the direct causes and effects of a target variable from observed data. Existing constraint-based local causal discovery methods use AND or OR rules in constructing the local causal skeleton, but using either rule alone is prone to produce cascading errors in the learned local causal skeleton, and thus impacting the inference of local causal relationships. On the other hand, directly applying score-based global causal discovery methods to local causal discovery may randomly return incorrect results due to the existence of local equivalence classes. To address the above issues, we propose a Hybrid Local Causal Discovery algorithm, called HLCD. Specifically, HLCD initially utilizes a constraint-based approach combined with the OR rule to obtain a candidate skeleton and then employs a score-based method to eliminate redundant portions in the candidate skeleton. Furthermore, during the local causal orientation phase, HLCD distinguishes between V-structures and equivalence classes by comparing the local structure scores between the two, thereby avoiding orientation interference caused by local equivalence classes. We conducted extensive experiments with seven state-of-the-art competitors on 14 benchmark Bayesian network datasets, and the experimental results demonstrate that HLCD significantly outperforms existing local causal discovery algorithms.

Despite the vast amount of information encoded in Knowledge Graphs (KGs), information about the class affiliation of entities remains often incomplete. Graph Convolutional Networks (GCNs) have been shown to be effective predictors of complete information about the class affiliation of entities in KGs. However, these models do not learn the class affiliation of entities in KGs incorporating the complexity of the task, which negatively affects the models prediction capabilities. To address this problem, we introduce a Markov process-based architecture into well-known GCN architectures. This end-to-end network learns the prediction of class affiliation of entities in KGs within a Markov process. The number of computational steps is learned during training using a geometric distribution. At the same time, the loss function combines insights from the field of evidential learning. The experiments show a performance improvement over existing models in several studied architectures and datasets. Based on the chosen hyperparameters for the geometric distribution, the expected number of computation steps can be adjusted to improve efficiency and accuracy during training.