Related papers: WorldCompass: Reinforcement Learning for Long-Hori…

Reinforcement Learning (RL) in various decision-making tasks of machine learning provides effective results with an agent learning from a stand-alone reward function. However, it presents unique challenges with large amounts of environment…

We study how to effectively leverage expert feedback to learn sequential decision-making policies. We focus on problems with sparse rewards and long time horizons, which typically pose significant challenges in reinforcement learning. We…

The aim of Reinforcement Learning (RL) in real-world applications is to create systems capable of making autonomous decisions by learning from their environment through trial and error. This paper emphasizes the importance of reward…

Reinforcement learning for training end-to-end autonomous driving models in closed-loop simulations is gaining growing attention. However, most simulation environments differ significantly from real-world conditions, creating a substantial…

Exploration in environments with sparse rewards has been a persistent problem in reinforcement learning (RL). Many tasks are natural to specify with a sparse reward, and manually shaping a reward function can result in suboptimal…

Robots have been successfully used to perform tasks with high precision. In real-world environments with sparse rewards and multiple goals, learning is still a major challenge and Reinforcement Learning (RL) algorithms fail to learn good…

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…

In recent years, autonomous networks have been designed with Predictive Quality of Service (PQoS) in mind, as a means for applications operating in the industrial and/or automotive sectors to predict unanticipated Quality of Service (QoS)…

Leveraging offline data is a promising way to improve the sample efficiency of online reinforcement learning (RL). This paper expands the pool of usable data for offline-to-online RL by leveraging abundant non-curated data that is…

Sparse-reward reinforcement learning (RL) can model a wide range of highly complex tasks. Solving sparse-reward tasks is RL's core premise, requiring efficient exploration coupled with long-horizon credit assignment, and overcoming these…

Much of model-based reinforcement learning involves learning a model of an agent's world, and training an agent to leverage this model to perform a task more efficiently. While these models are demonstrably useful for agents, every…

Post-training Vision-Language-Action (VLA) models via reinforcement learning (RL) in learned world models has emerged as an effective strategy to adapt to new tasks without costly real-world interactions. However, while using imagined…

Large-scale autoregressive models pretrained on next-token prediction and finetuned with reinforcement learning (RL) have achieved unprecedented success on many problem domains. During RL, these models explore by generating new outputs, one…

Fine-grained visual reasoning remains a core challenge for multimodal large language models (MLLMs). The recently introduced ReasonMap highlights this gap by showing that even advanced MLLMs struggle with spatial reasoning in structured and…

Reinforcement learning (RL) has achieved remarkable success in real-world decision-making across diverse domains, including gaming, robotics, online advertising, public health, and natural language processing. Despite these advances, a…

Reinforcement learning for agentic multimodal models often suffers from interaction collapse, where models learn to reduce tool usage and multi-turn reasoning, limiting the benefits of agentic behavior. We introduce PyVision-RL, a…

Reinforcement Learning (RL) algorithms often struggle with low training efficiency. A common approach to address this challenge is integrating model-based planning algorithms, such as Monte Carlo Tree Search (MCTS) or Value Iteration (VI),…

Conveying complex objectives to reinforcement learning (RL) agents can often be difficult, involving meticulous design of reward functions that are sufficiently informative yet easy enough to provide. Human-in-the-loop RL methods allow…

Designing rewards for Reinforcement Learning (RL) is challenging because it needs to convey the desired task, be efficient to optimize, and be easy to compute. The latter is particularly problematic when applying RL to robotics, where…

Vision-language-action (VLA) models that directly predict multi-step action chunks from current observations face inherent limitations due to constrained scene understanding and weak future anticipation capabilities. In contrast, video…