Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

RL policy training interval optimization research benchmarks · SOTA2 Research

RL policy training interval optimization

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

Indoor Lighting Trace Stair Access simulated 1000 nodes

89Policy Trainings Count

2

Jun 5, 2026

Indoor Lighting Trace Conference Room (simulated 1000 nodes)

Dynamic On-Policy

17Policy Trainings Count

2

Jun 5, 2026

Indoor Lighting Trace Door (simulated 1000 nodes)

89Policy Trainings Count

2

Jun 5, 2026

Indoor Lighting Trace Middle Office (simulated 1000 nodes)

Dynamic On-Policy

42Policy Trainings Count

2

Jun 5, 2026

Indoor Lighting Trace Window (simulated 1000 nodes)

89Number of Policy Trainings

2

Jun 5, 2026

Popular datasets

Indoor Lighting Trace

Follow for updates

Join SOTA2 Contact