Related papers: Manifold-Constrained Energy-Based Transition Model…

The increasing complexity of power grid management, driven by the emergence of prosumers and the demand for cleaner energy solutions, has needed innovative approaches to ensure stability and efficiency. This paper presents a novel approach…

An energy-based model (EBM) is a popular generative framework that offers both explicit density and architectural flexibility, but training them is difficult since it is often unstable and time-consuming. In recent years, various training…

Limited data has become a major bottleneck in scaling up offline imitation learning (IL). In this paper, we propose enhancing IL performance under limited expert data by introducing a pre-training stage that learns dynamics representations,…

We investigate the {\em power-down mechanism} which decides when a machine transitions between states such that the total energy consumption, characterized by execution cost, idle cost and switching cost, is minimized. In contrast to most…

Decision-focused learning (DFL) was recently proposed for stochastic optimization problems that involve unknown parameters. By integrating predictive modeling with an implicitly differentiable optimization layer, DFL has shown superior…

We present a machine learning (ML)-assisted framework bridging manifold learning, neural networks, Gaussian processes, and Equation-Free multiscale modeling, for (a) detecting tipping points in the emergent behavior of complex systems, and…

We introduce Equilibrium Matching (EqM), a generative modeling framework built from an equilibrium dynamics perspective. EqM discards the non-equilibrium, time-conditional dynamics in traditional diffusion and flow-based generative models…

Offline reinforcement learning (RL) faces a significant challenge of distribution shift. Model-free offline RL penalizes the Q value for out-of-distribution (OOD) data or constrains the policy closed to the behavior policy to tackle this…

Foundation models compress a large amount of information in a single, large neural network, which can then be queried for individual tasks. There are strong parallels between this widespread framework and offline goal-conditioned…

Distributionally robust offline reinforcement learning (RL) aims to find a policy that performs the best under the worst environment within an uncertainty set using an offline dataset collected from a nominal model. While recent advances in…

Offline reinforcement learning (RL) looks at learning how to optimally solve tasks using a fixed dataset of interactions from the environment. Many off-policy algorithms developed for online learning struggle in the offline setting as they…

Offline reinforcement learning (RL) aims at learning policies from previously collected static trajectory data without interacting with the real environment. Recent works provide a novel perspective by viewing offline RL as a generic…

This paper introduces the offline meta-reinforcement learning (offline meta-RL) problem setting and proposes an algorithm that performs well in this setting. Offline meta-RL is analogous to the widely successful supervised learning strategy…

Offline Reinforcement Learning (RL), which operates solely on static datasets without further interactions with the environment, provides an appealing alternative to learning a safe and promising control policy. The prevailing methods…

In offline reinforcement learning (RL), we seek to utilize offline data to evaluate (or learn) policies in scenarios where the data are collected from a distribution that substantially differs from that of the target policy to be evaluated.…

One of the key challenges in applying reinforcement learning to complex robotic control tasks is the need to gather large amounts of experience in order to find an effective policy for the task at hand. Model-based reinforcement learning…

Model predictive control (MPC) is capable of controlling nonlinear systems with guaranteed constraint satisfaction and stability. However, MPC requires solving optimization problems online periodically, which often exceeds the local…

Deep reinforcement learning has recently shown many impressive successes. However, one major obstacle towards applying such methods to real-world problems is their lack of data-efficiency. To this end, we propose the Bottleneck Simulator: a…

This paper studies the fundamental problem of learning multi-layer generator models. The multi-layer generator model builds multiple layers of latent variables as a prior model on top of the generator, which benefits learning complex data…

Multimodal generative models are crucial for various applications. We propose an approach that combines an expressive energy-based model (EBM) prior with Markov Chain Monte Carlo (MCMC) inference in the latent space for multimodal…