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

Goal-Conditioned Reinforcement Learning (Manipulation) research benchmarks · SOTA2 Research

Goal-Conditioned Reinforcement Learning (Manipulation)

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

puzzle-4x4-play state-based v0 (test)

Dual Goal Representations

23Success Rate

6

Feb 26, 2026

puzzle-3x3-play state-based v0 (test)

14Success Rate

6

Feb 26, 2026

scene-play state-based v0 (test)

Dual Goal Representations

72Success Rate

6

Feb 26, 2026

cube-double-play state-based v0 (test)

Dual Goal Representations

60Success Rate

6

Feb 26, 2026

Popular datasets

cube-double-play scene-play puzzle-3x3-play puzzle-play

Follow for updates

Join SOTA2 Contact