相关论文: Augmented World Models Facilitate Zero-Shot Dynami…

World models improve a learning agent's ability to efficiently operate in interactive and situated environments. This work focuses on the task of building world models of text-based game environments. Text-based games, or interactive…

While model-based reinforcement learning (MBRL) improves sample efficiency by learning world models from raw observations, existing methods struggle to generalize across structurally similar scenes and remain vulnerable to spurious…

Existing domain generalization aims to learn a generalizable model to perform well even on unseen domains. For many real-world machine learning applications, the data distribution often shifts gradually along domain indices. For example, a…

Deep reinforcement learning has proven to be a great success in allowing agents to learn complex tasks. However, its application to actual robots can be prohibitively expensive. Furthermore, the unpredictability of human behavior in…

Generative models such as diffusion have been employed as world models in offline reinforcement learning to generate synthetic data for more effective learning. Existing work either generates diffusion models one-time prior to training or…

Agentic reinforcement learning increasingly relies on experience-driven scaling, yet real-world environments remain non-adaptive, limited in coverage, and difficult to scale. World models offer a potential way to improve learning efficiency…

Reinforcement Learning (RL) has achieved impressive results in robotics, yet high-performing pipelines remain highly task-specific, with little reuse of prior data. Offline Model-based RL (MBRL) offers greater data efficiency by training…

Model-based control requires an accurate model of the system dynamics for precisely and safely controlling the robot in complex and dynamic environments. Moreover, in the presence of variations in the operating conditions, the model should…

In this work we present a method for leveraging data from one source to learn how to do multiple new tasks. Task transfer is achieved using a self-model that encapsulates the dynamics of a system and serves as an environment for…

Reinforcement learning has been demonstrated as a flexible and effective approach for learning a range of continuous control tasks, such as those used by robots to manipulate objects in their environment. But in robotics particularly,…

Learning has propelled the cutting edge of performance in robotic control to new heights, allowing robots to operate with high performance in conditions that were previously unimaginable. The majority of the work, however, assumes that the…

The next generation of autonomous agents must not only learn efficiently but also act reliably and adapt their behavior in open worlds. Standard approaches typically assume fixed tasks and environments with little or no novelty, which…

A generalist robot must be able to complete a variety of tasks in its environment. One appealing way to specify each task is in terms of a goal observation. However, learning goal-reaching policies with reinforcement learning remains a…

We study the problem of offline pre-training and online fine-tuning for reinforcement learning from high-dimensional observations in the context of realistic robot tasks. Recent offline model-free approaches successfully use online…

Developing control policies in simulation is often more practical and safer than directly running experiments in the real world. This applies to policies obtained from planning and optimization, and even more so to policies obtained from…

We introduce multi-task Visuo-Tactile World Models (VT-WM), which capture the physics of contact through touch reasoning. By complementing vision with tactile sensing, VT-WM better understands robot-object interactions in contact-rich…

Automated data augmentation has shown superior performance in image recognition. Existing works search for dataset-level augmentation policies without considering individual sample variations, which are likely to be sub-optimal. On the…

The training of autonomous agents often requires expensive and unsafe trial-and-error interactions with the environment. Nowadays several data sets containing recorded experiences of intelligent agents performing various tasks, spanning…

One of the great promises of robot learning systems is that they will be able to learn from their mistakes and continuously adapt to ever-changing environments. Despite this potential, most of the robot learning systems today are deployed…

Reinforcement learning often requires extensive training data. Simulation-to-real transfer offers a promising approach to address this challenge in robotics. While differentiable simulators offer improved sample efficiency through exact…