List your company

Continuous Control on HalfCheetah v5

13,996.2Average ReturnTQC
3,670.3526,351.1019,031.8511,712.599Feb 5, 2026Feb 10, 2026Feb 16, 2026Feb 21, 2026Feb 27, 2026Mar 4, 2026Mar 10, 2026

Evaluation results

MethodLinks
TQCActor Backbone=SAC2026.0213,996.2
DBCActor Backbone=TD32026.0213,787.8
DSACActor Backbone=SAC2026.0212,974
SACActor Backbone=SAC2026.0212,776.4
IQNActor Backbone=SAC2026.0210,930.2
VFActor Backbone=SAC2026.028,199.5
PDAEnvironment steps=1M, Seeds=10, Tests per epoch=102026.035,174.6
VDActor Backbone=SAC2026.024,284.8
PPOEnvironment steps=1M, Seeds=10, Tests per epoch=102026.034,067.5