Scaling self-supervised contrastive reinforcement learning (CRL) to 1000-layer Euclidean neural networks has enabled state-of-the-art goal-reaching performance, yet wall-clock time scales linearly with depth. We find that changing the geometry achieves stronger performance with far shallower networks. This matters in complex navigation environments, where walls can make route distance deviate substantially from Euclidean distance. In a U-shaped maze, we show that the longer the route, the more it deviates from Euclidean distance. Hyperbolic CRL addresses this mismatch by replacing Euclidean distances in CRL's contrastive objective with geodesic distances in hyperbolic space. On hard navigation tasks, inductive bias beats scale: depth 64 hyperbolic agents outperform 1024-layer-deep Euclidean networks while training more than $12 \times$ faster and using about $13 \times$ fewer parameters. We observe that hyperbolic agents behave qualitatively better in hard humanoid mazes, where they follow corridors to reach goals, whereas Euclidean agents try straight-line shortcuts over walls. Our results show that matching the representation geometry to the task can substitute for substantial network depth. Code is at https://github.com/Probabilistic-and-Interactive-ML/HypGCRL .
The Chinese University of Hong Kong（香港中文大学）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）
Deep visuomotor policy learning, which aims to map raw visual observation to action, achieves promising results in control tasks such as robotic manipulation and autonomous driving. However, it requires a huge number of online interactions with the training environment, which limits its real-world application. Compared to the popular unsupervised feature learning for visual recognition, feature pretraining for visuomotor control tasks is much less explored. In this work, we aim to pretrain policy representations for driving tasks by watching hours-long uncurated YouTube videos. Specifically, w…
Offline goal-conditioned reinforcement learning (GCRL) promises general-purpose skill learning in the form of reaching diverse goals from purely offline datasets. We propose $\textbf{Go}$al-conditioned $f$-$\textbf{A}$dvantage $\textbf{R}$egression (GoFAR), a novel regression-based offline GCRL algorithm derived from a state-occupancy matching perspective; the key intuition is that the goal-reaching task can be formulated as a state-occupancy matching problem between a dynamics-abiding imitator agent and an expert agent that directly teleports to the goal. In contrast to prior approaches, GoFA…
Compositional Transduction with Latent Analogies for Offline Goal-Conditioned Reinforcement Learning
Department of Electrical and Computer Engineering and ASRI, Seoul National University（电气与计算机工程系和首尔国立大学ASRI）；Independent researcher（独立研究者）；Robotics Institute, Carnegie Mellon University（卡内基梅隆大学机器人研究所）
Test-Time Graph Search for Goal-Conditioned Reinforcement Learning
Department of Computer Science, University of Toronto, Toronto, Canada（多伦多大学计算机科学系）；Vector Institute, Toronto, Canada（向量研究所）；University of Texas at Austin, Austin, USA（德克萨斯大学奥斯汀分校）；Harvard University, Cambridge, USA（哈佛大学）
Free from Bellman Completeness: Trajectory Stitching via Model-based Return-conditioned Supervised Learning
Institute for Interdisciplinary Information Sciences, Tsinghua University（清华大学交叉信息研究院）；Paul G. Allen School of Computer Science and Engineering, University of Washington（华盛顿大学保罗·G·艾伦计算机科学与工程学院）
ACT: Empowering Decision Transformer with Dynamic Programming via Advantage Conditioning
National Key Laboratory for Novel Software Technology, Nanjing University（南京大学计算机软件新技术全国重点实验室）；School of Artificial Intelligence, Nanjing University（南京大学人工智能学院）
MIT（麻省理工学院）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）
The need for efficiently comparing and representing datasets with unknown alignment spans various fields, from model analysis and comparison in machine learning to trend discovery in collections of medical datasets. We use manifold learning to compare the intrinsic geometric structures of different datasets by comparing their diffusion operators, symmetric positive-definite (SPD) matrices that relate to approximations of the continuous Laplace-Beltrami operator from discrete samples. Existing methods typically assume known data alignment and compare such operators in a pointwise manner. Instea…
SAMUeL: Efficient Vocal-Conditioned Music Generation via Soft Alignment Attention and Latent Diffusion
Division of Engineering Science University of Toronto（工程科学系 马尼托瓦大学）；Innovative Cognitive Computing Center King Mongkut's University of Technology Thonburi（创新认知计算中心 王后大学技术吞武里）
UC Berkeley（加州大学伯克利分校）；ICSI（国际计算机科学研究所）；Facebook AI Research（脸书人工智能研究院）
Hyperbolic space can naturally embed hierarchies, unlike Euclidean space. Hyperbolic Neural Networks (HNNs) exploit such representational power by lifting Euclidean features into hyperbolic space for classification, outperforming Euclidean neural networks (ENNs) on datasets with known semantic hierarchies. However, HNNs underperform ENNs on standard benchmarks without clear hierarchies, greatly restricting HNNs' applicability in practice. Our key insight is that HNNs' poorer general classification performance results from vanishing gradients during backpropagation, caused by their hybrid archi…
Decoupling Time and Space: A Temporally Conditioned Refinement for EEG Source Imaging
Berlin Institute for the Foundations of Learning and Data（柏林学习与数据基础研究所）；Technische Universität Berlin（柏林工业大学）；Korea University（高丽大学）；Max Planck Institut für Informatik（马克斯·普朗克信息学研究所）；Basque Center on Cognition, Brain and Language（巴斯克认知、大脑与语言中心）；Ikerbasque（伊克尔巴斯克基金会）
Can we ease the Injectivity Bottleneck on Lorentzian Manifolds for Graph Neural Networks?
Institute for Clarity in Documentation（清晰文档研究所）；Inria Paris-Rocquencourt（巴黎-罗克琴克特研究所）；Rajiv Gandhi University（拉贾维·甘地大学）；Tsinghua University（清华大学）；Palmer Research Laboratories（帕勒实验室）；Vellore Institute of Technology（韦洛尔理工学院）
