List your company

Reinforcement Learning on Humanoid

90,921,063Zero-Shot RewardOpen-Ended Neural Reward Functions
-3,636,841.438420,911,845.290845,460,532.0270,009,218.7492Feb 16, 2022Oct 17, 2022Jun 18, 2023Feb 16, 2024Oct 17, 2024Jun 17, 2025Feb 16, 2026

Evaluation results

MethodLinks
Open-Ended Neural Reward FunctionsEvaluation Mode=Zero-shot2022.0290,921,063—
SMACbatch size=1000, seeds=52026.014,625—
AC-SGDbatch size=1000, seeds=52026.014,539—
AC-CGbatch size=1000, seeds=52026.013,175—
AC-Adambatch size=1000, seeds=52026.013,105—
MAMBA + Minimum AttentionSteps=30M2025.052,553—
MAMBASteps=30M2025.052,453—
CT-SACHyperparameter Configuration Rank=top2026.02386.75—
CT-SACHyperparameter Configuration Rank=second2026.02379.75—
CT-SACHyperparameter Configuration Rank=third2026.02371.75—
CT-TD3Hyperparameter Configuration Rank=top2026.02337.23—
CT-TD3Hyperparameter Configuration Rank=second2026.02326.61—
CT-TD3Hyperparameter Configuration Rank=third2026.02295.94—
AC-KFACbatch size=1000, seeds=52026.01260.8—
SACHyperparameter Configuration Rank=top2026.0273.39—
SACHyperparameter Configuration Rank=second2026.0239.28—
TD3Hyperparameter Configuration Rank=top2026.022.28—
TD3Hyperparameter Configuration Rank=second2026.022.24—
SACHyperparameter Configuration Rank=third2026.022.12—
TD3Hyperparameter Configuration Rank=third2026.022.11—
q-LearningHyperparameter Configuration Rank=top2026.021.81—
q-LearningHyperparameter Configuration Rank=second2026.021.59—
TRPOHyperparameter Configuration Rank=top2026.021.39—
TRPOHyperparameter Configuration Rank=second2026.021.33—
TRPOHyperparameter Configuration Rank=third2026.021.3—
q-LearningHyperparameter Configuration Rank=third2026.021.28—
PPOHyperparameter Configuration Rank=top2026.021.18—
PPOHyperparameter Configuration Rank=second2026.021.17—
CPPOHyperparameter Configuration Rank=top2026.021.16—
PPOHyperparameter Configuration Rank=third2026.021.11—
CPPOHyperparameter Configuration Rank=second2026.021.08—
CPPOHyperparameter Configuration Rank=third2026.021.04—