Related papers: RL-ViGen: A Reinforcement Learning Benchmark for V…

Learning from previously collected data via behavioral cloning or offline reinforcement learning (RL) is a powerful recipe for scaling generalist agents by avoiding the need for expensive online learning. Despite strong generalization in…

Recently DeepSeek R1 has shown that reinforcement learning (RL) can substantially improve the reasoning capabilities of Large Language Models (LLMs) through a simple yet effective design. The core of R1 lies in its rule-based reward…

Effectively retrieving, reasoning and understanding visually rich information remains a challenge for RAG methods. Traditional text-based methods cannot handle visual-related information. On the other hand, current vision-based RAG…

End-to-end reinforcement learning on images showed significant progress in the recent years. Data-based approach leverage data augmentation and domain randomization while representation learning methods use auxiliary losses to learn…

While current benchmark reinforcement learning (RL) tasks have been useful to drive progress in the field, they are in many ways poor substitutes for learning with real-world data. By testing increasingly complex RL algorithms on…

Unifying diverse image generation tasks within a single framework remains a fundamental challenge in visual generation. While large language models (LLMs) achieve unification through task-agnostic data and generation, existing visual…

Graphical user interface (GUI)-based mobile agents automate digital tasks on mobile devices by interpreting natural-language instructions and interacting with the screen. While recent methods apply reinforcement learning (RL) to train…

Self-supervised learning and data augmentation have significantly reduced the performance gap between state and image-based reinforcement learning agents in continuous control tasks. However, it is still unclear whether current techniques…

Reinforcement Learning (RL) has achieved state-of-the-art results in domains such as robotics and games. We build on this previous work by applying RL algorithms to a selection of canonical online stochastic optimization problems with a…

Visual reinforcement learning (RL), which makes decisions directly from high-dimensional visual inputs, has demonstrated significant potential in various domains. However, deploying visual RL techniques in the real world remains challenging…

Visual Reinforcement Learning (RL) agents trained on limited views face significant challenges in generalizing their learned abilities to unseen views. This inherent difficulty is known as the problem of $\textit{view generalization}$. In…

While Reinforcement Learning (RL) has achieved remarkable success in language modeling, its triumph hasn't yet fully translated to visuomotor agents. A primary challenge in RL models is their tendency to overfit specific tasks or…

Episodic training, where an agent's environment is reset after every success or failure, is the de facto standard when training embodied reinforcement learning (RL) agents. The underlying assumption that the environment can be easily reset…

Reinforcement learning (RL) has emerged as a promising approach for eliciting reasoning chains before generating final answers. However, multimodal large language models (MLLMs) generate reasoning that lacks integration of visual…

Online reinforcement learning in complex tasks is time-consuming, as massive interaction steps are needed to learn the optimal Q-function.Vision-language action (VLA) policies represent a promising direction for solving diverse tasks;…

Reinforcement learning (RL) has recently shown strong potential in improving the reasoning capabilities of large language models and is now being actively extended to vision-language models (VLMs). However, existing RL applications in VLMs…

Producing agents that can generalize to a wide range of visually different environments is a significant challenge in reinforcement learning. One method for overcoming this issue is visual domain randomization, whereby at the start of each…

We introduce a method to address goal misgeneralization in reinforcement learning (RL), leveraging Large Language Model (LLM) feedback during training. Goal misgeneralization, a type of robustness failure in RL occurs when an agent retains…

Reinforcement learning (RL) promises a framework for near-universal problem-solving. In practice however, RL algorithms are often tailored to specific benchmarks, relying on carefully tuned hyperparameters and algorithmic choices. Recently,…

Manipulating objects is a hallmark of human intelligence, and an important task in domains such as robotics. In principle, Reinforcement Learning (RL) offers a general approach to learn object manipulation. In practice, however, domains…