相关论文: Improving Transformer World Models for Data-Effici…

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…

Frontier models have demonstrated exceptional capabilities following the integration of task-reward-based reinforcement learning (RL) into their training pipelines, enabling systems to evolve from pure reasoning models into sophisticated…

In-context learning enables transformer models to generalize to new tasks based solely on input prompts, without any need for weight updates. However, existing training paradigms typically rely on large, unstructured datasets that are…

Transformers are remarkably versatile, suggesting the existence of generic inductive biases beneficial across modalities. In this work, we explore a new way to instil such biases in vision transformers (ViTs) through pretraining on…

In order to mitigate the sample complexity of real-world reinforcement learning, common practice is to first train a policy in a simulator where samples are cheap, and then deploy this policy in the real world, with the hope that it…

Training robots for operation in the real world is a complex, time consuming and potentially expensive task. Despite significant success of reinforcement learning in games and simulations, research in real robot applications has not been…

Although reward models have been successful in improving multimodal large language models, the reward models themselves remain brutal and contain minimal information. Notably, existing reward models only mimic human annotations by assigning…

Recent work has shown that augmenting environments with language descriptions improves policy learning. However, for environments with complex language abstractions, learning how to ground language to observations is difficult due to…

This work presents WorldCompass, a novel Reinforcement Learning (RL) post-training framework for the long-horizon, interactive video-based world models, enabling them to explore the world more accurately and consistently based on…

We propose the use of latent space generative world models to address the covariate shift problem in autonomous driving. A world model is a neural network capable of predicting an agent's next state given past states and actions. By…

Reinforcement Learning (RL) methods are typically applied directly in environments to learn policies. In some complex environments with continuous state-action spaces, sparse rewards, and/or long temporal horizons, learning a good policy in…

Transformer-based models have achieved state-of-the-art results in many natural language processing tasks. The self-attention architecture allows transformer to combine information from all elements of a sequence into context-aware…

In many reinforcement learning tasks, the agent has to learn to interact with many objects of different types and generalize to unseen combinations and numbers of objects. Often a task is a composition of previously learned tasks (e.g.…

One of the fundamental challenges in reinforcement learning (RL) is the one of data efficiency: modern algorithms require a very large number of training samples, especially compared to humans, for solving environments with high-dimensional…

Model-based reinforcement learning (RL) is more sample efficient than model-free RL by using imaginary trajectories generated by the learned dynamics model. When the model is inaccurate or biased, imaginary trajectories may be deleterious…

Some of the most important tasks take place in environments which lack cheap and perfect simulators, thus hampering the application of model-free reinforcement learning (RL). While model-based RL aims to learn a dynamics model, in a more…

A long-standing goal of reinforcement learning is to acquire agents that can learn on training tasks and generalize well on unseen tasks that may share a similar dynamic but with different reward functions. The ability to generalize across…

In the present paper, we propose a decoder-free extension of Dreamer, a leading model-based reinforcement learning (MBRL) method from pixels. Dreamer is a sample- and cost-efficient solution to robot learning, as it is used to train latent…

Open-world novelty--a sudden change in the mechanics or properties of an environment--is a common occurrence in the real world. Novelty adaptation is an agent's ability to improve its policy performance post-novelty. Most reinforcement…

Adapting pretrained video generation models into controllable world models via latent actions is a promising step towards creating generalist world models. The dominant paradigm adopts a two-stage approach that trains latent action model…