相关论文: Reinforcement Learning with Videos: Combining Offl…

We propose to learn legged robot locomotion skills by watching thousands of wild animal videos from the internet, such as those featured in nature documentaries. Indeed, such videos offer a rich and diverse collection of plausible motion…

Robots operating in complex and uncertain environments face considerable challenges. Advanced robotic systems often rely on extensive datasets to learn manipulation tasks. In contrast, when humans are faced with unfamiliar tasks, such as…

We investigate the use of animal videos (observations) to improve Reinforcement Learning (RL) efficiency and performance in navigation tasks with sparse rewards. Motivated by theoretical considerations, we make use of weighted policy…

Reinforcement learning can enable robots to navigate to distant goals while optimizing user-specified reward functions, including preferences for following lanes, staying on paved paths, or avoiding freshly mowed grass. However, online…

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…

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…

Reinforcement learning from verifiable rewards (RLVR) has demonstrated remarkable effectiveness in improving the reasoning capabilities of large language models. As models evolve into natively multimodal architectures, extending RLVR to…

We consider real-world reinforcement learning (RL) of robotic manipulation tasks that involve both visuomotor skills and contact-rich skills. We aim to train a policy that maps multimodal sensory observations (vision and force) to a…

Reinforcement Learning is a mature technology, often suggested as a potential route towards Artificial General Intelligence, with the ambitious goal of replicating the wide range of abilities found in natural and artificial intelligence,…

Generative models have made significant progress in synthesizing visual content, including images, videos, and 3D/4D structures. However, they are typically trained with surrogate objectives such as likelihood or reconstruction loss, which…

Imitation by observation is an approach for learning from expert demonstrations that lack action information, such as videos. Recent approaches to this problem can be placed into two broad categories: training dynamics models that aim to…

Reinforcement learning from human feedback (RLHF) is a variant of reinforcement learning (RL) that learns from human feedback instead of relying on an engineered reward function. Building on prior work on the related setting of…

Recent unsupervised pre-training methods have shown to be effective on language and vision domains by learning useful representations for multiple downstream tasks. In this paper, we investigate if such unsupervised pre-training methods can…

We propose Reinforcement Learning with Explicit Human Values (RLEV), a method that aligns Large Language Model (LLM) optimization directly with quantifiable human value signals. While Reinforcement Learning with Verifiable Rewards (RLVR)…

Reward learning enables robots to learn adaptable behaviors from human input. Traditional methods model the reward as a linear function of hand-crafted features, but that requires specifying all the relevant features a priori, which is…

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…

Offline reinforcement learning (RL) enables policy optimization using static datasets, avoiding the risks and costs of extensive real-world exploration. However, it struggles with suboptimal offline behaviors and inaccurate value estimation…

Robotic reinforcement learning (RL) holds the promise of enabling robots to learn complex behaviors through experience. However, realizing this promise for long-horizon tasks in the real world requires mechanisms to reduce human burden in…

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…

Humans can quickly learn new behaviors by leveraging background world knowledge. In contrast, agents trained with reinforcement learning (RL) typically learn behaviors from scratch. We thus propose a novel approach that uses the vast…