相关论文: Better World Models Can Lead to Better Post-Traini…

Reinforcement learning (RL) agents make decisions using nothing but observations from the environment, and consequently, heavily rely on the representations of those observations. Though some recent breakthroughs have used vector-based…

Unlike quasi-static robotic manipulation tasks like pick-and-place, dynamic tasks such as non-prehensile manipulation pose greater challenges, especially for vision-based control. Successful control requires the extraction of features…

Planning with world models offers a powerful paradigm for robotic control. Conventional approaches train a model to predict future frames conditioned on current frames and actions, which can then be used for planning. However, the objective…

Next-token predictors often appear to develop internal representations of the latent world and its rules. The probabilistic nature of these models suggests a deep connection between the structure of the world and the geometry of probability…

World Models (WMs) have emerged as a promising approach for post-training Vision-Language-Action (VLA) policies to improve robustness and generalization under environmental changes. However, most WM-based post-training methods rely on…

Since hardware resources are limited, the objective of training deep learning models is typically to maximize accuracy subject to the time and memory constraints of training and inference. We study the impact of model size in this setting,…

World modelling, i.e. building a representation of the rules that govern the world so as to predict its evolution, is an essential ability for any agent interacting with the physical world. Recent applications of the Transformer…

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…

As reinforcement learning agents become increasingly deployed in real-world scenarios, predicting future agent actions and events during deployment is important for facilitating better human-agent interaction and preventing catastrophic…

Deep reinforcement learning has shown its advantages in real-time decision-making based on the state of the agent. In this stage, we solved the task of using a real robot to manipulate the cube to a given trajectory. The task is broken down…

The potential benefits of model-free reinforcement learning to real robotics systems are limited by its uninformed exploration that leads to slow convergence, lack of data-efficiency, and unnecessary interactions with the environment. To…

Recent advances in vision-language models have enabled mobile GUI agents to perceive visual interfaces and execute user instructions, but reliable prediction of action consequences remains critical for long-horizon and high-risk…

Reinforcement learning (RL) promises to expand the capabilities of language models, but it is unclear if current RL techniques promote the discovery of novel behaviors, or simply sharpen those already present in the base model. In this…

The emergence of pre-trained models has significantly impacted Natural Language Processing (NLP) and Computer Vision to relational datasets. Traditionally, these models are assessed through fine-tuned downstream tasks. However, this raises…

The performance of learned robot visuomotor policies is heavily dependent on the size and quality of the training dataset. Although large-scale robot and human datasets are increasingly available, embodiment gaps and mismatched action…

In the smart grid of the future, accurate load forecasts on the level of individual clients can help to balance supply and demand locally and to prevent grid outages. While the number of monitored clients will increase with the ongoing…

Model-based next state prediction and state value prediction are slow to converge. To address these challenges, we do the following: i) Instead of a neural network, we do model-based planning using a parallel memory retrieval system (which…

Action-conditioned video prediction models (often referred to as world models) have shown strong potential for robotics applications, but existing approaches are often slow and struggle to capture physically consistent interactions over…

This empirical study analyzes the effects of the pre-training corpus on the quality of learned transformer representations. We focus on the representation quality induced solely through pre-training. Our experiments show that pre-training…

Group-based reinforcement learning methods, like Group Relative Policy Optimization (GRPO), are widely used nowadays to post-train large language models. Despite their empirical success, they exhibit structural mismatches between reward…