Training visual reinforcement learning (RL) in practical scenarios presents a significant challenge, $\textit{i.e.,}$ RL agents suffer from low sample efficiency in environments with variations. While various approaches have attempted to alleviate this issue by disentanglement representation learning, these methods usually start learning from scratch without prior knowledge of the world. This paper, in contrast, tries to learn and understand underlying semantic variations from distracting videos via offline-to-online latent distillation and flexible disentanglement constraints. To enable effective cross-domain semantic knowledge transfer, we introduce an interpretable model-based RL framework, dubbed Disentangled World Models (DisWM). Specifically, we pretrain the action-free video prediction model offline with disentanglement regularization to extract semantic knowledge from distracting videos. The disentanglement capability of the pretrained model is then transferred to the world model through latent distillation. For finetuning in the online environment, we exploit the knowledge from the pretrained model and introduce a disentanglement constraint to the world model. During the adaptation phase, the incorporation of actions and rewards from online environment interactions enriches the diversity of the data, which in turn strengthens the disentangled representation learning. Experimental results validate the superiority of our approach on various benchmarks.

In recent years, the exceptional performance of generative models in generative tasks has sparked significant interest in their integration into decision-making processes. Due to their ability to handle complex data distributions and their strong model capacity, generative models can be effectively incorporated into decision-making systems by generating trajectories that guide agents toward high-reward state-action regions or intermediate sub-goals. This paper presents a comprehensive review of the application of generative models in decision-making tasks. We classify seven fundamental types of generative models: energy-based models, generative adversarial networks, variational autoencoders, normalizing flows, diffusion models, generative flow networks, and autoregressive models. Regarding their applications, we categorize their functions into three main roles: controllers, modelers and optimizers, and discuss how each role contributes to decision-making. Furthermore, we examine the deployment of these models across five critical real-world decision-making scenarios. Finally, we summarize the strengths and limitations of current approaches and propose three key directions for advancing next-generation generative directive models: high-performance algorithms, large-scale generalized decision-making models, and self-evolving and adaptive models.

On-robot Reinforcement Learning is a promising approach to train embodiment-aware policies for legged robots. However, the computational constraints of real-time learning on robots pose a significant challenge. We present a framework for efficiently learning quadruped locomotion in just 8 minutes of raw real-time training utilizing the sample efficiency and minimal computational overhead of the new off-policy algorithm CrossQ. We investigate two control architectures: Predicting joint target positions for agile, high-speed locomotion and Central Pattern Generators for stable, natural gaits. While prior work focused on learning simple forward gaits, our framework extends on-robot learning to omnidirectional locomotion. We demonstrate the robustness of our approach in different indoor and outdoor environments.

Mechanistic knowledge about the physical world is virtually always expressed via partial differential equations (PDEs). Recently, there has been a surge of interest in probabilistic PDE solvers -- Bayesian statistical models mostly based on Gaussian process (GP) priors which seamlessly combine empirical measurements and mechanistic knowledge. As such, they quantify uncertainties arising from e.g. noisy or missing data, unknown PDE parameters or discretization error by design. Prior work has established connections to classical PDE solvers and provided solid theoretical guarantees. However, scaling such methods to large-scale problems remains a fundamental challenge primarily due to dense covariance matrices. Our approach addresses the scalability issues by leveraging the Markov property of many commonly used GP priors. It has been shown that such priors are solutions to stochastic PDEs (SPDEs) which when discretized allow for highly efficient GP regression through sparse linear algebra. In this work, we show how to leverage this prior class to make probabilistic PDE solvers practical, even for large-scale nonlinear PDEs, through greatly accelerated inference mechanisms. Additionally, our approach also allows for flexible and physically meaningful priors beyond what can be modeled with covariance functions. Experiments confirm substantial speedups and accelerated convergence of our physics-informed priors in nonlinear settings.

In recent years, humanoid robots have garnered significant attention from both academia and industry due to their high adaptability to environments and human-like characteristics. With the rapid advancement of reinforcement learning, substantial progress has been made in the walking control of humanoid robots. However, existing methods still face challenges when dealing with complex environments and irregular terrains. In the field of perceptive locomotion, existing approaches are generally divided into two-stage methods and end-to-end methods. Two-stage methods first train a teacher policy in a simulated environment and then use distillation techniques, such as DAgger, to transfer the privileged information learned as latent features or actions to the student policy. End-to-end methods, on the other hand, forgo the learning of privileged information and directly learn policies from a partially observable Markov decision process (POMDP) through reinforcement learning. However, due to the lack of supervision from a teacher policy, end-to-end methods often face difficulties in training and exhibit unstable performance in real-world applications. This paper proposes an innovative two-stage perceptive locomotion framework that combines the advantages of teacher policies learned in a fully observable Markov decision process (MDP) to regularize and supervise the student policy. At the same time, it leverages the characteristics of reinforcement learning to ensure that the student policy can continue to learn in a POMDP, thereby enhancing the model's upper bound. Our experimental results demonstrate that our two-stage training framework achieves higher training efficiency and stability in simulated environments, while also exhibiting better robustness and generalization capabilities in real-world applications.

Inferring the graph structure from observed data is a key task in graph machine learning to capture the intrinsic relationship between data entities. While significant advancements have been made in learning the structure of homogeneous graphs, many real-world graphs exhibit heterogeneous patterns where nodes and edges have multiple types. This paper fills this gap by introducing the first approach for heterogeneous graph structure learning (HGSL). To this end, we first propose a novel statistical model for the data-generating process (DGP) of heterogeneous graph data, namely hidden Markov networks for heterogeneous graphs (H2MN). Then we formalize HGSL as a maximum a-posterior estimation problem parameterized by such DGP and derive an alternating optimization method to obtain a solution together with a theoretical justification of the optimization conditions. Finally, we conduct extensive experiments on both synthetic and real-world datasets to demonstrate that our proposed method excels in learning structure on heterogeneous graphs in terms of edge type identification and edge weight recovery.

Counterfactual explanations indicate the smallest change in input that can translate to a different outcome for a machine learning model. Counterfactuals have generated immense interest in high-stakes applications such as finance, education, hiring, etc. In several use-cases, the decision-making process often relies on an ensemble of models rather than just one. Despite significant research on counterfactuals for one model, the problem of generating a single counterfactual explanation for an ensemble of models has received limited interest. Each individual model might lead to a different counterfactual, whereas trying to find a counterfactual accepted by all models might significantly increase cost (effort). We propose a novel strategy to find the counterfactual for an ensemble of models using the perspective of entropic risk measure. Entropic risk is a convex risk measure that satisfies several desirable properties. We incorporate our proposed risk measure into a novel constrained optimization to generate counterfactuals for ensembles that stay valid for several models. The main significance of our measure is that it provides a knob that allows for the generation of counterfactuals that stay valid under an adjustable fraction of the models. We also show that a limiting case of our entropic-risk-based strategy yields a counterfactual valid for all models in the ensemble (worst-case min-max approach). We study the trade-off between the cost (effort) for the counterfactual and its validity for an ensemble by varying degrees of risk aversion, as determined by our risk parameter knob. We validate our performance on real-world datasets.

Recent advances in language model (LM) agents and function calling have enabled autonomous, feedback-driven systems to solve problems across various digital domains. To better understand the unique limitations of LM agents, we introduce RefactorBench, a benchmark consisting of 100 large handcrafted multi-file refactoring tasks in popular open-source repositories. Solving tasks within RefactorBench requires thorough exploration of dependencies across multiple files and strong adherence to relevant instructions. Every task is defined by 3 natural language instructions of varying specificity and is mutually exclusive, allowing for the creation of longer combined tasks on the same repository. Baselines on RefactorBench reveal that current LM agents struggle with simple compositional tasks, solving only 22% of tasks with base instructions, in contrast to a human developer with short time constraints solving 87%. Through trajectory analysis, we identify various unique failure modes of LM agents, and further explore the failure mode of tracking past actions. By adapting a baseline agent to condition on representations of state, we achieve a 43.9% improvement in solving RefactorBench tasks. We further extend our state-aware approach to encompass entire digital environments and outline potential directions for future research. RefactorBench aims to support the study of LM agents by providing a set of real-world, multi-hop tasks within the realm of code. "Repetition is the root of all software evil" -- Martin Fowler Large language models (LLMs) have been quickly acquiring new capabilities (Bubeck et al., 2023), leading towards adoption of AI-powered systems in various formats and domains. The increasing usage of LLM powered tools like Github Copilot have greatly improved the capability of developers in software development tasks (Peng et al., 2023). More recently, an emphasis on multi-step execution through LLM feedback loops has unlocked the ability to solve harder problems within a variety of fields (Reed et al., 2022; Sumers et al., 2024; Yao & Narasimhan, 2023), including parts of software engineering. This new paradigm of solving larger software tasks has led to the construction of a variety of new automated software engineering (ASE) systems, most being structured as LM agents (Wang et al., 2024c; Cognition.ai, Evaluations for such systems are currently largely comprised from real world data on Github (Jimenez et al., 2024; LaBash et al., 2024). While being the strongest open-source signal for software engineering tasks at scale, Github is inherently noisy through its snapshot nature, also requiring strong filtration and validation testing for reliable evaluations (Chowdhury et al., 2024; Bowman & Dahl, 2021).

Recently, with the development of Multi-agent reinforcement learning (MARL), adaptive traffic signal control (ATSC) has achieved satisfactory results. In traffic scenarios with multiple intersections, MARL treats each intersection as an agent and optimizes traffic signal control strategies through learning and real-time decision-making. Considering that observation distributions of intersections might be different in real-world scenarios, shared parameter methods might lack diversity and thus lead to high generalization requirements in the shared-policy network. A typical solution is to increase the size of network parameters. However, simply increasing the scale of the network does not necessarily improve policy generalization, which is validated in our experiments. Accordingly, an approach that considers both the personalization of intersections and the efficiency of parameter sharing is required. To this end, we propose Hyper-Action Multi-Head Proximal Policy Optimization (HAMH-PPO), a Centralized Training with Decentralized Execution (CTDE) MARL method that utilizes a shared PPO policy network to deliver personalized policies for intersections with non-iid observation distributions. The centralized critic in HAMH-PPO uses graph attention units to calculate the graph representations of all intersections and outputs a set of value estimates with multiple output heads for each intersection. The decentralized execution actor takes the local observation history as input and output distributions of action as well as a so-called hyper-action to balance the multiple values estimated from the centralized critic to further guide the updating of TSC policies. The combination of hyper-action and multi-head values enables multiple agents to share a single actor-critic while achieving personalized policies.

The key to robot-assisted rehabilitation lies in the design of the human-machine interface, which must accommodate the needs of both patients and machines. Current interface designs primarily focus on machine control algorithms, often requiring patients to spend considerable time adapting. In this paper, we introduce a novel approach based on the Cooperative Adaptive Markov Decision Process (CAMDPs) model to address the fundamental aspects of the interactive learning process, offering theoretical insights and practical guidance. We establish sufficient conditions for the convergence of CAMDPs and ensure the uniqueness of Nash equilibrium points. Leveraging these conditions, we guarantee the system's convergence to a unique Nash equilibrium point. Furthermore, we explore scenarios with multiple Nash equilibrium points, devising strategies to adjust both Value Evaluation and Policy Improvement algorithms to enhance the likelihood of converging to the global minimal Nash equilibrium point. Through numerical experiments, we illustrate the effectiveness of the proposed conditions and algorithms, demonstrating their applicability and robustness in practical settings. The proposed conditions for convergence and the identification of a unique optimal Nash equilibrium contribute to the development of more effective adaptive systems for human users in robot-assisted rehabilitation.