arXiv:2604. 08780v2 Announce Type: replace-cross Abstract: World models promise a paradigm shift in robotics, where an agent learns the physics of its environment once and then acquires behaviors efficiently.
arXiv:2607. 11624v1 Announce Type: cross Abstract: Reinforcement learning (RL) algorithms classically suffer from poor sample efficiency.
Reinforcement learning (RL) algorithms classically suffer from poor sample efficiency. In robotics, a recent line of work has emerged addressing this problem by encoding physics priors in the learning process.
arXiv:2508. 18066v2 Announce Type: replace-cross Abstract: Controlling high-dimensional and nonlinear musculoskeletal models of the human body is a foundational scientific challenge.
arXiv:2608. 01506v1 Announce Type: cross Abstract: Humans readily adapt their movements as their bodies change through aging, injury, or load carrying, but learning-based robot policies often break when hardware properties shift.
arXiv:2509. 06296v2 Announce Type: replace-cross Abstract: Traditional on-policy reinforcement learning (RL) controllers for quadrupedal locomotion often suffer from low data efficiency, requiring millions of interactions with simulated environments to achieve stable control.
arXiv:2607. 00442v1 Announce Type: cross Abstract: Reinforcement learning (RL) for quadruped locomotion commonly depends on fixed, hand-crafted, and Markovian reward functions that limit both interpretability of learned policies and lack explicit control over gait behaviors.
arXiv:2607. 24083v1 Announce Type: new Abstract: Reinforcement learning can produce robust humanoid controllers, but each new task is typically trained as a separate policy with its own reward design and training process.
arXiv:2510. 18348v2 Announce Type: replace-cross Abstract: State-of-the-art perceptive Reinforcement Learning controllers for legged robots typically either (i) impose oscillator-or IK-based gait priors that constrain the action space, bias policy optimization, and limit adaptability across robot morphologies, or (ii) operate "blind," making them unable to anticipate hind-leg terrain and brittle to observation noise.
arXiv:2607. 12114v1 Announce Type: cross Abstract: A humanoid that can walk should not relearn locomotion from scratch to jog or run.
arXiv:2508. 16943v3 Announce Type: replace-cross Abstract: Physics-based human motion control can make a simulated character walk, sit, and manipulate objects with high physical realism.
arXiv:2607. 07370v1 Announce Type: cross Abstract: In embodied intelligence systems, the motion controller serves as the critical bridge between semantic reasoning and physical execution.
arXiv:2606. 13886v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models excel at mapping visual inputs and natural language instructions directly to robotic control policies.