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

Reinforcement Learning on ML1 benchmark leaderboard · SOTA2 Research

Research Benchmarks

Reinforcement Learning on ML1

4Environment Steps (M)SAC

Updated 1mo ago

Evaluation Results

Method	Links
SAC2025.03		4
TOP-ERL2025.03		4
T-SAC2025.03		1

SOTA Paper

SAC

Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor

Dataset

ML1

Follow for updates

Join SOTA2 Contact

Related Benchmarks

Reinforcement Learning on Box-Pushing dense Robotic Manipulation on Box-Pushing dense (max 20M steps)Robotic Manipulation on Box-Pushing sparse (max 20M steps)Meta-Reinforcement Learning on Meta-World ML1 max 5M steps Reinforcement Learning on Box-Pushing sparse