Minimum-flow GFlowNets on graphs encode optimal transport plans, with the learned policy recovering the optimal coupling between source and target distributions.
TorchRL: A data-driven decision- making library for PyTorch
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
abstract
PyTorch has ascended as a premier machine learning framework, yet it lacks a native and comprehensive library for decision and control tasks suitable for large development teams dealing with complex real-world data and environments. To address this issue, we propose TorchRL, a generalistic control library for PyTorch that provides well-integrated, yet standalone components. We introduce a new and flexible PyTorch primitive, the TensorDict, which facilitates streamlined algorithm development across the many branches of Reinforcement Learning (RL) and control. We provide a detailed description of the building blocks and an extensive overview of the library across domains and tasks. Finally, we experimentally demonstrate its reliability and flexibility and show comparative benchmarks to demonstrate its computational efficiency. TorchRL fosters long-term support and is publicly available on GitHub for greater reproducibility and collaboration within the research community. The code is open-sourced on GitHub.
years
2026 4representative citing papers
Neural-network agents trained in social environments learn hybrid navigation strategies that combine individual landmark use with social following, with strategy shifts driven by the ratio of skilled to unskilled social agents.
A unified homogeneous graph framework with feature homogenization enables linear-complexity RL policies for job shop scheduling that generalize zero-shot via structural saturation at balanced job-machine ratios.
IR-SIM is a YAML-defined simulator for mobile robot navigation that supports text-prompt scenario creation, policy training, benchmarking, and bridging to higher-fidelity or real-world settings.
citing papers explorer
-
Your GFlowNet Secretly Learns an Optimal Transport Plan
Minimum-flow GFlowNets on graphs encode optimal transport plans, with the learned policy recovering the optimal coupling between source and target distributions.
-
Social-spatial dependencies for learning visual navigation
Neural-network agents trained in social environments learn hybrid navigation strategies that combine individual landmark use with social following, with strategy shifts driven by the ratio of skilled to unskilled social agents.
-
Scalable Production Scheduling: Linear Complexity via Unified Homogeneous Graphs
A unified homogeneous graph framework with feature homogenization enables linear-complexity RL policies for job shop scheduling that generalize zero-shot via structural saturation at balanced job-machine ratios.
-
IR-SIM: A Lightweight Skill-Native Simulator for Navigation, Learning, and Benchmarking
IR-SIM is a YAML-defined simulator for mobile robot navigation that supports text-prompt scenario creation, policy training, benchmarking, and bridging to higher-fidelity or real-world settings.