OGBench

OgBench: Benchmarking Graph Neural Networks on Omics Data OgBench is the first benchmark suite for graph-level prediction in the n ≪ p regime characteristic of omics data, where the number of patient samples n is much smaller than the number of nodes (genes or proteins) p per graph. Datasets This repository contains fo

Papers using OGBench (37)

TD-JEPA: Latent-predictive Representations for Zero-Shot Reinforcement Learning2025 · 9 citesDEAS: DEtached value learning with Action Sequence for Scalable Offline RL2025 · 6 citesCIG: Exploration via Conditional Information Gain2026Latent Representation Alignment for Offline Goal-Conditioned Reinforcement Learning2026Exploiting Local Dynamics Regularity for Reusable Skills in Offline Hierarchical RL2026Adaptive Coarse-to-Fine Subgoal Refinement for Long-Horizon Offline Goal-Conditioned Reinforcement Learning2026Drift Q-Learning2026Adaptive Q-Chunking for Offline-to-Online Reinforcement Learning2026Path-Coupled Bellman Flows for Distributional Reinforcement Learning2026ACSAC: Adaptive Chunk Size Actor-Critic with Causal Transformer Q-Network2026Aligning Flow Map Policies with Optimal Q-Guidance2026Q-Flow: Stable and Expressive Reinforcement Learning with Flow-Based Policy2026Offline Reinforcement Learning with Universal Horizon Models2026Compositional Transduction with Latent Analogies for Offline Goal-Conditioned Reinforcement Learning2026Efficient Hierarchical Implicit Flow Q-learning for Offline Goal-conditioned Reinforcement Learning2026Reinforcement Learning via Value Gradient Flow2026Preserve Support, Not Correspondence: Dynamic Routing for Offline Reinforcement Learning2026Latent Policy Steering through One-Step Flow Policies2026Chunk-Guided Q-Learning2026Zero-Shot Off-Policy Learning2026Laplacian Representations for Decision-Time Planning2026ReFORM: Reflected Flows for On-support Offline RL via Noise Manipulation2026Data-Efficient Hierarchical Goal-Conditioned Reinforcement Learning via Normalizing Flows2026Mean Flow Policy with Instantaneous Velocity Constraint for One-step Action Generation2026Flow Actor-Critic for Offline Reinforcement Learning2026Guided Flow Policy: Learning from High-Value Actions in Offline Reinforcement Learning2025Planning as Descent: Goal-Conditioned Latent Trajectory Synthesis in Learned Energy Landscapes2025One-Step Generative Policies with Q-Learning: A Reformulation of MeanFlow2025ASTRO: Adaptive Stitching via Dynamics-Guided Trajectory Rollouts2025Dual Goal Representations2025Test-Time Graph Search for Goal-Conditioned Reinforcement Learning2025Unleashing Flow Policies with Distributional Critics2025Enhancing Math Reasoning in Small-sized LLMs via Preview Difficulty-Aware Intervention2025Option-aware Temporally Abstracted Value for Offline Goal-Conditioned Reinforcement Learning2025DHP: Discrete Hierarchical Planning for Hierarchical Reinforcement Learning Agents2025Flow Q-Learning2025OGBench: Benchmarking Offline Goal-Conditioned RL2024