Related papers: Accelerating Representation Learning with View-Con…
Vision-Language-Action (VLA) models have emerged as a promising framework that unifies perception, reasoning, and control for robot manipulation by adapting pretrained vision-language models (VLMs) to action prediction. However, VLM-derived…
Many real-world applications of reinforcement learning (RL) require the agent to deal with high-dimensional observations such as those generated from a megapixel camera. Prior work has addressed such problems with representation learning,…
In this paper, we introduce a learning-based vision dynamics approach to nonlinear model predictive control for autonomous vehicles, coined LVD-NMPC. LVD-NMPC uses an a-priori process model and a learned vision dynamics model used to…
We consider the general class of time-homogeneous stochastic dynamical systems, both discrete and continuous, and study the problem of learning a representation of the state that faithfully captures its dynamics. This is instrumental to…
In many robotic applications, some aspects of the system dynamics can be modeled accurately while others are difficult to obtain or model. We present a novel reinforcement learning (RL) method for continuous state and action spaces that…
Classical pixel-based Visual Servoing (VS) approaches offer high accuracy but suffer from a limited convergence area due to optimization nonlinearity. Modern deep learning-based VS methods overcome traditional vision issues but lack…
State-of-the-art visual recognition and detection systems increasingly rely on large amounts of training data and complex classifiers. Therefore it becomes increasingly expensive both to manually annotate datasets and to keep running times…
We study self-supervised video representation learning, which is a challenging task due to 1) lack of labels for explicit supervision; 2) unstructured and noisy visual information. Existing methods mainly use contrastive loss with video…
We propose learning via retracing, a novel self-supervised approach for learning the state representation (and the associated dynamics model) for reinforcement learning tasks. In addition to the predictive (reconstruction) supervision in…
In reinforcement learning (RL), state representations are key to dealing with large or continuous state spaces. While one of the promises of deep learning algorithms is to automatically construct features well-tuned for the task they try to…
Recent studies have greatly improved reinforcement learning, and an increased interest in real-world implementation has emerged. In many cases, the implementation is challenged by time-varying disturbances as it introduces hidden states,…
We propose a self-supervised algorithm to learn representations from egocentric video data. Recently, significant efforts have been made to capture humans interacting with their own environments as they go about their daily activities. In…
Markov decision processes (MDPs) are a well studied framework for solving sequential decision making problems under uncertainty. Exact methods for solving MDPs based on dynamic programming such as policy iteration and value iteration are…
The objective of this paper is self-supervised learning of spatio-temporal embeddings from video, suitable for human action recognition. We make three contributions: First, we introduce the Dense Predictive Coding (DPC) framework for…
In real-world applications with large state and action spaces, reinforcement learning (RL) typically employs function approximations to represent core components like the policies, value functions, and dynamics models. Although powerful…
In this paper, we propose a novel learning scheme for self-supervised video representation learning. Motivated by how humans understand videos, we propose to first learn general visual concepts then attend to discriminative local areas for…
General-purpose, intelligent, learning agents cycle through sequences of observations, actions, and rewards that are complex, uncertain, unknown, and non-Markovian. On the other hand, reinforcement learning is well-developed for small…
System identification, also known as learning forward models, transfer functions, system dynamics, etc., has a long tradition both in science and engineering in different fields. Particularly, it is a recurring theme in Reinforcement…
We develop an approach to learning visual representations that embraces multimodal data, driven by a combination of intra- and inter-modal similarity preservation objectives. Unlike existing visual pre-training methods, which solve a proxy…
Learning procedural-aware video representations is a key step towards building agents that can reason about and execute complex tasks. Existing methods typically address this problem by aligning visual content with textual descriptions at…