Humans excel at adapting perceptions and actions to diverse environments, enabling efficient interaction with the external world. This adaptive capability relies on the biological nervous system (BNS), which activates different brain regions for distinct tasks. Meta-learning similarly trains machines to handle multiple tasks but relies on a fixed network structure, not as flexible as BNS. To investigate the role of flexible network structure (FNS) in meta-learning, we conduct extensive empirical and theoretical analyses, finding that model performance is tied to structure, with no universally optimal pattern across tasks. This reveals the crucial role of FNS in meta-learning, ensuring meta-learning to generate the optimal structure for each task, thereby maximizing the performance and learning efficiency of meta-learning. Motivated by this insight, we propose to define, measure, and model FNS in meta-learning. First, we define that an effective FNS should possess frugality, plasticity, and sensitivity. Then, to quantify FNS in practice, we present three measurements for these properties, collectively forming the \emph{structure constraint} with theoretical supports. Building on this, we finally propose Neuromodulated Meta-Learning (NeuronML) to model FNS in meta-learning. It utilizes bi-level optimization to update both weights and structure with the structure constraint. Extensive theoretical and empirical evaluations demonstrate the effectiveness of NeuronML on various tasks. Code is publicly available at \href{https://github.com/WangJingyao07/NeuronML}{https://github.com/WangJingyao07/NeuronML}.

We consider regret minimization in low-rank MDPs with fixed transition and adversarial losses. Previous work has investigated this problem under either full-information loss feedback with unknown transitions (Zhao et al., 2024), or bandit loss feedback with known transition (Foster et al., 2022). First, we improve the $poly(d, A, H)T^{5/6}$ regret bound of Zhao et al. (2024) to $poly(d, A, H)T^{2/3}$ for the full-information unknown transition setting, where d is the rank of the transitions, A is the number of actions, H is the horizon length, and T is the number of episodes. Next, we initiate the study on the setting with bandit loss feedback and unknown transitions. Assuming that the loss has a linear structure, we propose both model based and model free algorithms achieving $poly(d, A, H)T^{2/3}$ regret, though they are computationally inefficient. We also propose oracle-efficient model-free algorithms with $poly(d, A, H)T^{4/5}$ regret. We show that the linear structure is necessary for the bandit case without structure on the reward function, the regret has to scale polynomially with the number of states. This is contrary to the full-information case (Zhao et al., 2024), where the regret can be independent of the number of states even for unstructured reward function.

Cryptocurrencies have gained popularity due to their transparency, security, and accessibility compared to traditional financial systems, with Bitcoin, introduced in 2009, leading the market. Bitcoin's security relies on blockchain technology - a decentralized ledger consisting of a consensus and an incentive mechanism. The consensus mechanism, Proof of Work (PoW), requires miners to solve difficult cryptographic puzzles to add new blocks, while the incentive mechanism rewards them with newly minted bitcoins. However, as Bitcoin's acceptance grows, it faces increasing threats from attacks targeting these mechanisms, such as selfish mining, double-spending, and block withholding. These attacks compromise security, efficiency, and reward distribution. Recent research shows that these attacks can be combined with each other or with either malicious strategies, such as network-layer attacks, or non-malicious strategies, like honest mining. These combinations lead to more sophisticated attacks, increasing the attacker's success rates and profitability. Therefore, understanding and evaluating these attacks is essential for developing effective countermeasures and ensuring long-term security. This paper begins by examining individual attacks executed in isolation and their profitability. It then explores how combining these attacks with each other or with other malicious and non-malicious strategies can enhance their overall effectiveness and profitability. The analysis further explores how the deployment of attacks such as selfish mining and block withholding by multiple competing mining pools against each other impacts their economic returns. Lastly, a set of design guidelines is provided, outlining areas future work should focus on to prevent or mitigate the identified threats.

Generating simulations to train intelligent agents in game-playing and robotics from natural language input, from user input or task documentation, remains an open-ended challenge. Existing approaches focus on parts of this challenge, such as generating reward functions or task hyperparameters. Unlike previous work, we introduce FACTORSIM that generates full simulations in code from language input that can be used to train agents. Exploiting the structural modularity specific to coded simulations, we propose to use a factored partially observable Markov decision process representation that allows us to reduce context dependence during each step of the generation. For evaluation, we introduce a generative simulation benchmark that assesses the generated simulation code's accuracy and effectiveness in facilitating zero-shot transfers in reinforcement learning settings. We show that FACTORSIM outperforms existing methods in generating simulations regarding prompt alignment (e.g., accuracy), zero-shot transfer abilities, and human evaluation. We also demonstrate its effectiveness in generating robotic tasks.

Rationing of healthcare resources is a challenging decision that policy makers and providers may be forced to make during a pandemic, natural disaster, or mass casualty event. Well-defined guidelines to triage scarce life-saving resources must be designed to promote transparency, trust, and consistency. To facilitate buy-in and use during high-stress situations, these guidelines need to be interpretable and operational. We propose a novel data-driven model to compute interpretable triage guidelines based on policies for Markov Decision Process that can be represented as simple sequences of decision trees ("tree policies"). In particular, we characterize the properties of optimal tree policies and present an algorithm based on dynamic programming recursions to compute good tree policies. We utilize this methodology to obtain simple, novel triage guidelines for ventilator allocations for COVID-19 patients, based on real patient data from Montefiore hospitals. We also compare the performance of our guidelines to the official New York State guidelines that were developed in 2015 (well before the COVID-19 pandemic). Our empirical study shows that the number of excess deaths associated with ventilator shortages could be reduced significantly using our policy. Our work highlights the limitations of the existing official triage guidelines, which need to be adapted specifically to COVID-19 before being successfully deployed.

Model stealing, where a learner tries to recover an unknown model via carefully chosen queries, is a critical problem in machine learning, as it threatens the security of proprietary models and the privacy of data they are trained on. In recent years, there has been particular interest in stealing large language models (LLMs). In this paper, we aim to build a theoretical understanding of stealing language models by studying a simple and mathematically tractable setting. We study model stealing for Hidden Markov Models (HMMs), and more generally low-rank language models. We assume that the learner works in the conditional query model, introduced by Kakade, Krishnamurthy, Mahajan and Zhang. Our main result is an efficient algorithm in the conditional query model, for learning any low-rank distribution. In other words, our algorithm succeeds at stealing any language model whose output distribution is low-rank. This improves upon the previous result by Kakade, Krishnamurthy, Mahajan and Zhang, which also requires the unknown distribution to have high "fidelity", a property that holds only in restricted cases. There are two key insights behind our algorithm: First, we represent the conditional distributions at each timestep by constructing barycentric spanners among a collection of vectors of exponentially large dimension. Second, for sampling from our representation, we iteratively solve a sequence of convex optimization problems that involve projection in relative entropy to prevent compounding of errors over the length of the sequence. This is an interesting example where, at least theoretically, allowing a machine learning model to solve more complex problems at inference time can lead to drastic improvements in its performance.

Country instability is a global issue, with unpredictably high levels of instability thwarting socio-economic growth and possibly causing a slew of negative consequences. As a result, uncertainty prediction models for a country are becoming increasingly important in the real world, and they are expanding to provide more input from 'big data' collections, as well as the interconnectedness of global economies and social networks. This has culminated in massive volumes of qualitative data from outlets like television, print, digital, and social media, necessitating the use of artificial intelligence (AI) tools like machine learning to make sense of it all and promote predictive precision [1]. The Global Database of Activities, Voice, and Tone (GDELT Project) records broadcast, print, and web news in over 100 languages every second of every day, identifying the people, locations, organisations, counts, themes, outlets, and events that propel our global community and offering a free open platform for computation on the entire world. The main goal of our research is to investigate how, when our data grows more voluminous and fine-grained, we can conduct a more complex methodological analysis of political conflict. The GDELT dataset, which was released in 2012, is the first and potentially the most technologically sophisticated publicly accessible dataset on political conflict.

Traffic signal control is crucial for managing congestion in urban networks. Existing myopic pressure-based control methods focus only on immediate upstream links, leading to suboptimal green time allocation and increased network delays. Effective signal control, however, inherently requires a broader spatial scope, as traffic conditions further upstream can significantly impact traffic at the current location. This paper introduces a novel concept based on the Markov chain theory, namely multi-hop upstream pressure, that generalizes the conventional pressure to account for traffic conditions beyond the immediate upstream links. This farsighted and compact metric informs the deep reinforcement learning agent to preemptively clear the present queues, guiding the agent to optimize signal timings with a broader spatial awareness. Simulations on synthetic and realistic (Toronto) scenarios demonstrate controllers utilizing multi-hop upstream pressure significantly reduce overall network delay by prioritizing traffic movements based on a broader understanding of upstream congestion.

Taking into account future risk is essential for an autonomously operating robot to find online not only the best but also a safe action to execute. In this paper, we build upon the recently introduced formulation of probabilistic belief-dependent constraints. We present an anytime approach employing the Monte Carlo Tree Search (MCTS) method in continuous domains. Unlike previous approaches, our method assures safety anytime with respect to the currently expanded search tree without relying on the convergence of the search. We prove convergence in probability with an exponential rate of a version of our algorithms and study proposed techniques via extensive simulations. Even with a tiny number of tree queries, the best action found by our approach is much safer than the baseline. Moreover, our approach constantly finds better than the baseline action in terms of objective. This is because we revise the values and statistics maintained in the search tree and remove from them the contribution of the pruned actions.

Language agents have demonstrated promising capabilities in automating web-based tasks, though their current reactive approaches still underperform largely compared to humans. While incorporating advanced planning algorithms, particularly tree search methods, could enhance these agents' performance, implementing tree search directly on live websites poses significant safety risks and practical constraints due to irreversible actions such as confirming a purchase. In this paper, we introduce a novel paradigm that augments language agents with model-based planning, pioneering the innovative use of large language models (LLMs) as world models in complex web environments. Our method, WebDreamer, builds on the key insight that LLMs inherently encode comprehensive knowledge about website structures and functionalities. Specifically, WebDreamer uses LLMs to simulate outcomes for each candidate action (e.g., "what would happen if I click this button?") using natural language descriptions, and then evaluates these imagined outcomes to determine the optimal action at each step. Empirical results on two representative web agent benchmarks with online interaction -- VisualWebArena and Mind2Web-live -- demonstrate that WebDreamer achieves substantial improvements over reactive baselines. By establishing the viability of LLMs as world models in web environments, this work lays the groundwork for a paradigm shift in automated web interaction. More broadly, our findings open exciting new avenues for future research into 1) optimizing LLMs specifically for world modeling in complex, dynamic environments, and 2) model-based speculative planning for language agents.