AI Paper Atlas

Research map / Optimization / Optimizers

Scalable Planning with Tensorflow for Hybrid Nonlinear Domains

Ga Wu, Buser Say, Scott Sanner

NeurIPS 2017 · Optimization › Optimizers · approach: Differentiating through embedded optimization · 12 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use Tensorflow backpropagation planning with RMSProp instead of fminconHybrid nonlinear planning · Nonlinear domains: Navigation, Reservoir Control, and HVACplan costImproved
Use Tensorflow backpropagation planning with RMSProp instead of a domain-specific heuristicHybrid planning · Linear and nonlinear benchmark domainsplan costImproved
Use Tensorflow with RMSProp rather than MILP optimizationHybrid planning · Linear domainsplan costMixed
Use Tensorflow with RMSProp instead of fminconNonlinear Reservoir Control planning · Reservoir Control, horizon 60optimization speed: 16 times fasterImproved
Use Tensorflow with RMSProp instead of fminconNonlinear Reservoir Control planning · Reservoir Control, horizon 120optimization speed: hundreds of times fasterImproved
Use RMSProp rather than the other four tested Tensorflow optimizersTensorflow planning · HVACconvergence speedImproved
Use Adagrad or Adadelta rather than RMSPropTensorflow planning · HVACoptimization progressHurt
Set the learning rate to 0.1 instead of 0.001 (ablation)Tensorflow with RMSProp · HVACinitial convergence speedImproved
Set the learning rate to 0.1 instead of 0.001 (ablation)Tensorflow with RMSProp · HVACbest final score reachedHurt
Set the learning rate to 0.01 (ablation)Tensorflow with RMSProp · HVACconvergence to near-optimal scoreImproved
Use a larger learning rate rather than a smaller one (ablation)Tensorflow with RMSProp · HVACinitial convergence speedMixed
Scale nonlinear planning to 576,000 continuous action parameters across 100 parallel instancesTensorflow with RMSProp · HVAC nonlinear, horizon 96convergence time: 576,000 actions; 4 minutesImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy