Reinforcement learning (RL) in large or infinite state spaces is notoriously challenging, both theoretically (where worst-case sample and computational complexities must scale with state space cardinality) and experimentally (where function approximation and policy gradient techniques often scale poorly and suffer from instability and high variance). One line of research attempting to address these difficulties makes the natural assumption that we are given a collection of heuristic base or $\textit{constituent}$ policies upon which we would like to improve in a scalable manner. In this work we aim to compete with the $\textit{max-following policy}$, which at each state follows the action of whichever constituent policy has the highest value. The max-following policy is always at least as good as the best constituent policy, and may be considerably better. Our main result is an efficient algorithm that learns to compete with the max-following policy, given only access to the constituent policies (but not their value functions). In contrast to prior work in similar settings, our theoretical results require only the minimal assumption of an ERM oracle for value function approximation for the constituent policies (and not the global optimal policy or the max-following policy itself) on samplable distributions. We illustrate our algorithm's experimental effectiveness and behavior on several robotic simulation testbeds.

Increasing evidence suggests that many deployed AI systems do not sufficiently support end-user interaction and information needs. Engaging end-users in the design of these systems can reveal user needs and expectations, yet effective ways of engaging end-users in the AI explanation design remain under-explored. To address this gap, we developed a design method, called AI-DEC, that defines four dimensions of AI explanations that are critical for the integration of AI systems -- communication content, modality, frequency, and direction -- and offers design examples for end-users to design AI explanations that meet their needs. We evaluated this method through co-design sessions with workers in healthcare, finance, and management industries who regularly use AI systems in their daily work. Findings indicate that the AI-DEC effectively supported workers in designing explanations that accommodated diverse levels of performance and autonomy needs, which varied depending on the AI system's workplace role and worker values. We discuss the implications of using the AI-DEC for the user-centered design of AI explanations in real-world systems.

Augmenting large language models (LLMs) with external tools has emerged as a promising approach to extend their utility, empowering them to solve practical tasks. Existing work typically empowers LLMs as tool users with a manually designed workflow, where the LLM plans a series of tools in a step-by-step manner, and sequentially executes each tool to obtain intermediate results until deriving the final answer. However, they suffer from two challenges in realistic scenarios: (1) The handcrafted control flow is often ad-hoc and constraints the LLM to local planning; (2) The LLM is instructed to use only manually demonstrated tools or well-trained Python functions, which limits its generalization to new tools. In this work, we first propose Automatic Tool Chain (ATC), a framework that enables the LLM to act as a multi-tool user, which directly utilizes a chain of tools through programming. To scale up the scope of the tools, we next propose a black-box probing method. This further empowers the LLM as a tool learner that can actively discover and document tool usages, teaching themselves to properly master new tools. For a comprehensive evaluation, we build a challenging benchmark named ToolFlow, which diverges from previous benchmarks by its long-term planning scenarios and complex toolset. Experiments on both existing datasets and ToolFlow illustrate the superiority of our framework.

Advancements in language foundation models have primarily fueled the recent surge in artificial intelligence. In contrast, generative learning of non-textual modalities, especially videos, significantly trails behind language modeling. This thesis chronicles our endeavor to build multi-task models for generating videos and other modalities under diverse conditions, as well as for understanding and compression applications. Given the high dimensionality of visual data, we pursue concise and accurate latent representations. Our video-native spatial-temporal tokenizers preserve high fidelity. We unveil a novel approach to mapping bidirectionally between visual observation and interpretable lexical terms. Furthermore, our scalable visual token representation proves beneficial across generation, compression, and understanding tasks. This achievement marks the first instances of language models surpassing diffusion models in visual synthesis and a video tokenizer outperforming industry-standard codecs. Within these multi-modal latent spaces, we study the design of multi-task generative models. Our masked multi-task transformer excels at the quality, efficiency, and flexibility of video generation. We enable a frozen language model, trained solely on text, to generate visual content. Finally, we build a scalable generative multi-modal transformer trained from scratch, enabling the generation of videos containing high-fidelity motion with the corresponding audio given diverse conditions. Throughout the course, we have shown the effectiveness of integrating multiple tasks, crafting high-fidelity latent representation, and generating multiple modalities. This work suggests intriguing potential for future exploration in generating non-textual data and enabling real-time, interactive experiences across various media forms.

Large language models (LLMs) have been increasingly employed for (interactive) decision-making, via the development of LLM-based autonomous agents. Despite their emerging successes, the performance of LLM agents in decision-making has not been fully investigated through quantitative metrics, especially in the multi-agent setting when they interact with each other, a typical scenario in real-world LLM-agent applications. To better understand the limits of LLM agents in these interactive environments, we propose to study their interactions in benchmark decision-making settings in online learning and game theory, through the performance metric of \emph{regret}. We first empirically study the {no-regret} behaviors of LLMs in canonical (non-stationary) online learning problems, as well as the emergence of equilibria when LLM agents interact through playing repeated games. We then provide some theoretical insights into the no-regret behaviors of LLM agents, under certain assumptions on the supervised pre-training and the rationality model of human decision-makers who generate the data. Notably, we also identify (simple) cases where advanced LLMs such as GPT-4 fail to be no-regret. To promote the no-regret behaviors, we propose a novel \emph{unsupervised} training loss of \emph{regret-loss}, which, in contrast to the supervised pre-training loss, does not require the labels of (optimal) actions. We then establish the statistical guarantee of generalization bound for regret-loss minimization, followed by the optimization guarantee that minimizing such a loss may automatically lead to known no-regret learning algorithms. Our further experiments demonstrate the effectiveness of our regret-loss, especially in addressing the above ``regrettable'' cases.

We employ Large language models (LLMs) such as GPT-fine-tuning on the LLaMa-2, Mixtral 8 7B, 4 (OpenAI, 2023), BLOOM (Le Scao et al, Gemma, and conduct a comprehensive evaluation 2023), LLaMa-2 (Touvron et al, 2023), Mistral of Vietnamese LLMs across various scenarios and (Jiang et al., 2023), Mixtral (Jiang et al., 2024), settings. Throughout the thorough evaluation process, Gemma (Team et al., 2024) have made significant we observe the following: (i) larger language contributions to the field of natural language processing models exhibit unseen capabilities compared to (NLP). Despite their advancements, a gap smaller counterparts; (ii) larger language models remains in their specialization for many languages, tend to manifest more biases, produce uncalibrated including Vietnamese. This paper addresses the results, and are more susceptible to the influence development and evaluation of Vietnamese-centric of input prompts; (iii) the quality of training or LLMs. Vietnam, with a population surpassing 100 fine-tuning datasets is the key for unlocking LLM million, ranks as the 16th most populous country performance. Our key contributions include: globally.

We give a model-based agent that builds a Python program representing its knowledge of the world based on its interactions with the environment. The world model tries to explain its interactions, while also being optimistic about what reward it can achieve. We define this optimism as a logical constraint between a program and a planner. We study our agent on gridworlds, and on task planning, finding our approach is more sample-efficient compared to deep RL, more compute-efficient compared to ReAct-style agents, and that it can transfer its knowledge across environments by editing its code.

The drive to develop artificial neural networks that efficiently utilize resources has generated significant interest in bio-inspired Spiking Neural Networks (SNNs). These networks are particularly attractive due to their potential in applications requiring low power and memory. This potential is further enhanced by the ability to perform online local learning, enabling them to adapt to dynamic environments. This requires the model to be adaptive in a self-supervised manner. While self-supervised learning has seen great success in many deep learning domains, its application for online local learning in multi-layer SNNs remains underexplored. In this paper, we introduce the "EchoSpike Predictive Plasticity" (ESPP) learning rule, a pioneering online local learning rule designed to leverage hierarchical temporal dynamics in SNNs through predictive and contrastive coding. We validate the effectiveness of this approach using benchmark datasets, demonstrating that it performs on par with current state-of-the-art supervised learning rules. The temporal and spatial locality of ESPP makes it particularly well-suited for low-cost neuromorphic processors, representing a significant advancement in developing biologically plausible self-supervised learning models for neuromorphic computing at the edge.

Posets are discrete mathematical structures which are ubiquitous in a broad range of data analysis and machine learning applications. Research connecting posets to the data science domain has been ongoing for many years. In this paper, a comprehensive review of a wide range of studies on data analysis and machine learning using posets are examined in terms of their theory, algorithms and applications. In addition, the applied lattice theory domain of formal concept analysis will also be highlighted in terms of its machine learning applications.

Large policies pretrained on diverse robot datasets have the potential to transform robotic learning: instead of training new policies from scratch, such generalist robot policies may be finetuned with only a little in-domain data, yet generalize broadly. However, to be widely applicable across a range of robotic learning scenarios, environments, and tasks, such policies need to handle diverse sensors and action spaces, accommodate a variety of commonly used robotic platforms, and finetune readily and efficiently to new domains. In this work, we aim to lay the groundwork for developing open-source, widely applicable, generalist policies for robotic manipulation. As a first step, we introduce Octo, a large transformer-based policy trained on 800k trajectories from the Open X-Embodiment dataset, the largest robot manipulation dataset to date. It can be instructed via language commands or goal images and can be effectively finetuned to robot setups with new sensory inputs and action spaces within a few hours on standard consumer GPUs. In experiments across 9 robotic platforms, we demonstrate that Octo serves as a versatile policy initialization that can be effectively finetuned to new observation and action spaces. We also perform detailed ablations of design decisions for the Octo model, from architecture to training data, to guide future research on building generalist robot models.