Related papers: Robotic Offline RL from Internet Videos via Value-…

Offline reinforcement learning (RL) aims to learn from historical data without requiring (costly) access to the environment. To facilitate offline RL research, we previously introduced NeoRL, which highlighted that datasets from real-world…

Foundation models pre-trained on massive unlabeled datasets have revolutionized natural language and computer vision, exhibiting remarkable generalization capabilities, thus highlighting the importance of pre-training. Yet, efforts in…

Reinforcement learning (RL) can refine Vision-Language-Action (VLA) policies beyond behavior cloning, but real-world RL remains expensive due to extensive rollouts, resets, supervision, and safety risks. Action-conditioned video world…

Offline Reinforcement Learning (ORL) enablesus to separately study the two interlinked processes of reinforcement learning: collecting informative experience and inferring optimal behaviour. The second step has been widely studied in 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…

Visual Odometry (VO) is essential to downstream mobile robotics and augmented/virtual reality tasks. Despite recent advances, existing VO methods still rely on heuristic design choices that require several weeks of hyperparameter tuning by…

Learning to produce efficient movement behaviour for humanoid robots from scratch is a hard problem, as has been illustrated by the "Learning to run" competition at NIPS 2017. The goal of this competition was to train a two-legged model of…

Drawing upon the intuition that aligning different modalities to the same semantic embedding space would allow models to understand states and actions more easily, we propose a new perspective to the offline reinforcement learning (RL)…

Offline preference-based reinforcement learning (PbRL) typically operates in two phases: first, use human preferences to learn a reward model and annotate rewards for a reward-free offline dataset; second, learn a policy by optimizing the…

We present a novel method for collaborative robots (cobots) to learn manipulation tasks and perform them in a human-like manner. Our method falls under the learn-from-observation (LfO) paradigm, where robots learn to perform tasks by…

In deep Reinforcement Learning (RL), value functions are typically approximated using deep neural networks and trained via mean squared error regression objectives to fit the true value functions. Recent research has proposed an alternative…

The growing disparity between the exponential scaling of computational resources and the finite growth of high-quality text data now constrains conventional scaling approaches for large language models (LLMs). To address this challenge, we…

Reinforcement learning (RL) is widely used to produce robust robotic manipulation policies, but fine-tuning vision-language-action (VLA) models with RL can be unstable due to inaccurate value estimates and sparse supervision at intermediate…

Offline reinforcement learning (RL) is an effective tool for real-world recommender systems with its capacity to model the dynamic interest of users and its interactive nature. Most existing offline RL recommender systems focus on…

Cross-domain offline reinforcement learning (RL) aims to learn a policy in the target domain with a limited target domain dataset and a source domain dataset that exhibits a dynamics shift. Training directly on the original source dataset…

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…

Visual model-based reinforcement learning (RL) has the potential to enable sample-efficient robot learning from visual observations. Yet the current approaches typically train a single model end-to-end for learning both visual…

Recent advances in deep learning have shown significant potential for solving combinatorial optimization problems in real-time. Unlike traditional methods, deep learning can generate high-quality solutions efficiently, which is crucial for…

Our research investigates the challenges Deep Reinforcement Learning (DRL) faces in complex, Partially Observable Markov Decision Processes (POMDP) such as autonomous driving (AD), and proposes a solution for vision-based navigation in…

Offline post-training adapts a pretrained robot policy to a target dataset by supervised regression on recorded actions. In practice, robot datasets are heterogeneous: they mix embodiments, camera setups, and demonstrations of varying…