REVIEW 9 cited by
TorchRL: A data-driven decision-making library for PyTorch
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original 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.
Forward citations
Cited by 9 Pith papers
-
Reinforcement Learning Increases Wind Farm Power Production by Enabling Closed-Loop Collaborative Control
A closed-loop RL controller dynamically yaws turbines in LES and raises wind farm power by 4.30%, nearly doubling the 2.19% gain of static Bayesian-optimized yaw angles.
-
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 soci...
-
Latent Spherical Flow Policy for Reinforcement Learning with Combinatorial Actions
A spherical flow-matching policy over latent cost directions, mapped to feasible actions by a combinatorial solver with a vMF-smoothed value critic, beats prior combinatorial-RL baselines by 20.6% on four benchmark tasks.
-
Plug-and-Play Benchmarking of Reinforcement Learning Algorithms for Large-Scale Flow Control
FluidGym is a PyTorch-only, fully differentiable benchmark with 13 flow-control environments, MARL support, and public baselines.
-
Quality-of-Service Aware LLM Routing for Edge Computing with Multiple Experts
A DRL router using graph attention state abstraction and QoS-aware rewards improves average QoS by up to 35.78% over four baselines in simulated edge LLM routing.
-
Adaptive Destruction Processes for Diffusion Samplers
Learnable destruction processes with decoupled variances improve few-step discrete-time diffusion samplers on benchmarks and in GAN latent space.
-
CleanQRL: Lightweight Single-file Implementations of Quantum Reinforcement Learning Algorithms
The paper introduces CleanQRL, a collection of single-file implementations of quantum reinforcement learning algorithms designed to make QRL research easier to replicate and compare.
-
Synthesis of Model Predictive Control and Reinforcement Learning: Survey and Classification
A survey that classifies MPC+RL hybrids by algorithmic role, with tables of about 50 works, a theory review, and a software overview.
-
ObjectRL: An Object-Oriented Reinforcement Learning Codebase
ObjectRL is an object-oriented deep RL codebase whose class hierarchy mirrors RL components, demonstrated via a DRND extension and MuJoCo benchmark runs.
Discussion (0). Continue with ORCID to comment.