相关论文: Reinforcement Learning from Wild Animal Videos

We study how robots can autonomously learn skills that require a combination of navigation and grasping. While reinforcement learning in principle provides for automated robotic skill learning, in practice reinforcement learning in the real…

Deep reinforcement learning has seen successful implementations on humanoid robots to achieve dynamic walking. However, these implementations have been so far successful in simple environments void of obstacles. In this paper, we aim to…

Learning from demonstration (LfD) is useful in settings where hand-coding behaviour or a reward function is impractical. It has succeeded in a wide range of problems but typically relies on manually generated demonstrations or specially…

Scaling deep learning to massive and diverse internet data has driven remarkable breakthroughs in domains such as video generation and natural language processing. Robot learning, however, has thus far failed to replicate this success and…

Legged robots are physically capable of traversing a wide range of challenging environments, but designing controllers that are sufficiently robust to handle this diversity has been a long-standing challenge in robotics. Reinforcement…

Natural environments such as forests and grasslands are challenging for robotic navigation because of the false perception of rigid obstacles from high grass, twigs, or bushes. In this work, we present Wild Visual Navigation (WVN), an…

Learning from Demonstrations (LfD) and Reinforcement Learning (RL) have enabled robot agents to accomplish complex tasks. Reward Machines (RMs) enhance RL's capability to train policies over extended time horizons by structuring high-level…

Learning from visual data opens the potential to accrue a large range of manipulation behaviors by leveraging human demonstrations without specifying each of them mathematically, but rather through natural task specification. In this paper,…

Quadrupedal robots resemble the physical ability of legged animals to walk through unstructured terrains. However, designing a controller for quadrupedal robots poses a significant challenge due to their functional complexity and requires…

Learning controllers that reproduce legged locomotion in nature has been a long-time goal in robotics and computer graphics. While yielding promising results, recent approaches are not yet flexible enough to be applicable to legged systems…

This study investigates a method to guide and control fish schools using virtual fish trained with reinforcement learning. We utilize 2D virtual fish displayed on a screen to overcome technical challenges such as durability and movement…

Reinforcement learning (RL)-based motion imitation methods trained on demonstration data can effectively learn natural and expressive motions with minimal reward engineering but often struggle to generalize to novel environments. We address…

While reinforcement learning (RL) has the potential to enable robots to autonomously acquire a wide range of skills, in practice, RL usually requires manual, per-task engineering of reward functions, especially in real world settings where…

Mastering robotic manipulation skills through reinforcement learning (RL) typically requires the design of shaped reward functions. Recent developments in this area have demonstrated that using sparse rewards, i.e. rewarding the agent only…

Animals such as rabbits and birds can instantly generate locomotion behavior in reaction to a dynamic, approaching object, such as a person or a rock, despite having possibly never seen the object before and having limited perception of the…

Robot learning of manipulation skills is hindered by the scarcity of diverse, unbiased datasets. While curated datasets can help, challenges remain in generalizability and real-world transfer. Meanwhile, large-scale "in-the-wild" video…

Humanoid robots have demonstrated robust locomotion capabilities using Reinforcement Learning (RL)-based approaches. Further, to obtain human-like behaviors, existing methods integrate human motion-tracking or motion prior in the RL…

We introduce ReWiND, a framework for learning robot manipulation tasks solely from language instructions without per-task demonstrations. Standard reinforcement learning (RL) and imitation learning methods require expert supervision through…

This article proposes a method for learning and robotic replication of dynamic collaborative tasks from offline videos. The objective is to extend the concept of learning from demonstration (LfD) to dynamic scenarios, benefiting from widely…

Observing a human demonstrator manipulate objects provides a rich, scalable and inexpensive source of data for learning robotic policies. However, transferring skills from human videos to a robotic manipulator poses several challenges, not…