Related papers: Boltzmann priors for Implicit Transfer Operators

Transductive learning is a supervised machine learning task in which, unlike in traditional inductive learning, the unlabelled data that require labelling are a finite set and are available at training time. Similarly to inductive learning…

Temporal Interaction Graphs (TIGs) are widely utilized to represent real-world systems. To facilitate representation learning on TIGs, researchers have proposed a series of TIG models. However, these models are still facing two tough gaps…

Edge robotics involves frequent exchanges of large-volume multi-modal data. Existing methods ignore the interdependency between robotic functionalities and communication conditions, leading to excessive communication overhead. This paper…

Multi-Agent Reinforcement Learning involves agents that learn together in a shared environment, leading to emergent dynamics sensitive to initial conditions and parameter variations. A Dynamical Systems approach, which studies the evolution…

Learning-based solutions for long-tailed recognition face difficulties in generalizing on balanced test datasets. Due to imbalanced data prior, the learned \textit{a posteriori} distribution is biased toward the most frequent (head)…

Model Predictive Path Integral (MPPI) control is a powerful sampling-based strategy for nonlinear autonomous systems. However, its performance is often bottlenecked by the fidelity of nominal dynamics. We propose ICODE-MPPI, a robust…

Transient instability in nonlinear stochastic dynamical systems is a fundamental limitation in safety-critical aerospace applications, particularly during powered descent and landing where failure is driven by finite-time excursions rather…

Long-horizon dynamical prediction is fundamental in robotics and control, underpinning canonical methods like model predictive control. Yet, many systems and disturbance phenomena are difficult to model due to effects like nonlinearity,…

Faced with problems of increasing complexity, recent research in Bayesian Optimisation (BO) has focused on adapting deep probabilistic models as flexible alternatives to Gaussian Processes (GPs). In a similar vein, this paper investigates…

The predictive information, the mutual information between the past and future, has been shown to be a useful representation learning auxiliary loss for training reinforcement learning agents, as the ability to model what will happen next…

This paper presents an efficient model predictive path integral (MPPI) control framework for systems with complex nonlinear dynamics. To improve the computational efficiency of classic MPPI while preserving control performance, we replace…

Non-prehensile manipulation is challenging due to complex contact interactions between objects, the environment, and robots. Model-based approaches can efficiently generate complex trajectories of robots and objects under contact…

Multi-turn human-AI collaboration is fundamental to deploying interactive services such as adaptive tutoring, conversational recommendation, and professional consultation. However, optimizing these interactions via reinforcement learning is…

Real-world electricity consumption prediction may involve different tasks, e.g., prediction for different time steps ahead or different geo-locations. These tasks are often solved independently without utilizing some common problem-solving…

We establish that there are properties of quantum many-body dynamics which are efficiently learnable if we are given access to out-of-time-order correlators (OTOCs), but which require exponentially many operations in the system size if we…

Training deep networks and tuning hyperparameters on large datasets is computationally intensive. One of the primary research directions for efficient training is to reduce training costs by selecting well-generalizable subsets of training…

Modeling and control of nonlinear dynamics are critical in robotics, especially in scenarios with unpredictable external influences and complex dynamics. Traditional cascaded modular control pipelines often yield suboptimal performance due…

Current approaches to model-based offline reinforcement learning often incorporate uncertainty-based reward penalization to address the distributional shift problem. These approaches, commonly known as pessimistic value iteration, use Monte…

Restricted Boltzmann Machines (RBMs) are powerful tools for modeling complex systems and extracting insights from data, but their training is hindered by the slow mixing of Markov Chain Monte Carlo (MCMC) processes, especially with highly…

Task-oriented object grasping and rearrangement are critical skills for robots to accomplish different real-world manipulation tasks. However, they remain challenging due to partial observations of the objects and shape variations in…