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:2607. 11624v1 Announce Type: cross Abstract: Reinforcement learning (RL) algorithms classically suffer from poor sample efficiency.
arXiv:2608. 12063v1 Announce Type: cross Abstract: Integrating locomotion and manipulation is essential for robot autonomy, but scaling standard Reinforcement Learning (RL) to complex tasks is severely bottlenecked by the slow, manual process of dense reward shaping.
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.
Integrating locomotion and manipulation is essential for robot autonomy, but scaling standard Reinforcement Learning (RL) to complex tasks is severely bottlenecked by the slow, manual process of dense reward shaping. To bypass this limitation, we leverage Sample-based Model Predictive Control (SMPC) entirely in simulation as an automated, rapidly tunable expert to generate massive offline datasets.
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: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:2510. 12363v4 Announce Type: replace-cross Abstract: The pretraining-finetuning paradigm has facilitated numerous transformative advancements in artificial intelligence research in recent years.
arXiv:2607. 26985v1 Announce Type: cross Abstract: Deep reinforcement policy learning directly in physical robots (on-robot learning) remains bottlenecked by slow wall-clock training times.
arXiv:2608. 02069v1 Announce Type: cross Abstract: Developing deployable locomotion policies through conventional reinforcement learning often requires complex reward engineering and expensive training times.
arXiv:2603. 13707v3 Announce Type: replace-cross Abstract: Humanoid loco-manipulation requires coordinated task-space motion planning with stable loco-manipulation command tracking under complex robot-environment dynamics and long-horizon tasks.
arXiv:2607. 06824v1 Announce Type: cross Abstract: Physics-informed learning promises data-efficient and stable dynamics prediction, yet its strongest geometric guarantees have largely remained confined to closed conservative systems.
arXiv:2606. 02194v1 Announce Type: new Abstract: Distilling expert demonstration data into large generative models using behavioral cloning is a scalable approach to learning capable policies for robotic control, particularly for dexterous manipulation.