Related papers: Persistent Robot World Models: Stabilizing Multi-S…
Reward design remains a critical bottleneck in visual reinforcement learning (RL) for robotic manipulation. In simulated environments, rewards are conventionally designed based on the distance to a target position. However, such precise…
Deep reinforcement learning (RL) has emerged as a promising approach for autonomously acquiring complex behaviors from low level sensor observations. Although a large portion of deep RL research has focused on applications in video games…
Deploying learned control policies in real-world environments poses a fundamental challenge. When system dynamics change unexpectedly, performance degrades until models are retrained on new data. We introduce Reflexive World Models (RWM), a…
The strong performance of large vision-language models (VLMs) trained with reinforcement learning (RL) has motivated similar approaches for fine-tuning vision-language-action (VLA) models in robotics. Many recent works fine-tune VLAs…
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…
Reinforcement Learning (RL)-based control system has received considerable attention in recent decades. However, in many real-world problems, such as Batch Process Control, the environment is uncertain, which requires expensive interaction…
Predictive models have been at the core of many robotic systems, from quadrotors to walking robots. However, it has been challenging to develop and apply such models to practical robotic manipulation due to high-dimensional sensory…
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 work highlights that video world modeling, alongside vision-language pre-training, establishes a fresh and independent foundation for robot learning. Intuitively, video world models provide the ability to imagine the near future by…
Reinforcement learning (RL) is a powerful approach for robot learning. However, model-free RL (MFRL) requires a large number of environment interactions to learn successful control policies. This is due to the noisy RL training updates and…
Reinforcement learning (RL) promises to unlock capabilities beyond imitation learning for Vision-Language-Action (VLA) models, but its requirement for massive real-world interaction prevents direct deployment on physical robots. Recent work…
Recently, safe reinforcement learning (RL) with the actor-critic structure for continuous control tasks has received increasing attention. It is still challenging to learn a near-optimal control policy with safety and convergence…
Generalist robot policies can now perform a wide range of manipulation skills, but evaluating and improving their ability with unfamiliar objects and instructions remains a significant challenge. Rigorous evaluation requires a large number…
Simulation-to-reality reinforcement learning (RL) faces the critical challenge of reconciling discrepancies between simulated and real-world dynamics, which can severely degrade agent performance. A promising approach involves learning…
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…
Humanoid robots have attracted significant attention in recent years. Reinforcement Learning (RL) is one of the main ways to control the whole body of humanoid robots. RL enables agents to complete tasks by learning from environment…
World models aim to improve robotic decision making by predicting the consequences of actions. However, in practice, their predictions often become unreliable once the robot encounters states outside the training distribution, limiting…
Post-training is essential for turning pretrained generalist robot policies into reliable task-specific controllers, but existing human-in-the-loop pipelines remain tied to physical execution: each correction requires robot time, scene…
An oft-ignored challenge of real-world reinforcement learning is that the real world does not pause when agents make learning updates. As standard simulated environments do not address this real-time aspect of learning, most available…
The ability to plan into the future while utilizing only raw high-dimensional observations, such as images, can provide autonomous agents with broad capabilities. Visual model-based reinforcement learning (RL) methods that plan future…