List your company

Continuous Control on MuJoCo HalfCheetah v4 (test)

15,227Mean Episodic ReturnFP-DRL
326.44,194.8258,063.2511,931.675Apr 1, 2026Apr 8, 2026Apr 16, 2026Apr 24, 2026May 2, 2026May 10, 2026May 18, 2026

Evaluation results

MethodLinks
FP-DRL2026.0415,227512
SAC2026.0413,629994
SAC-FLOW2026.0412,6090
DSAC-T2026.0411,694171
DACER2026.0410,277399
TD32026.048,8240
RATArchitecture=Shared actor-critic networks, Seeds=5 random seeds2026.054,629.2—
PPOArchitecture=Shared actor-critic networks, Seeds=5 random seeds2026.054,146—
ACKTRArchitecture=Shared actor-critic networks, Seeds=5 random seeds2026.053,630.9—
SophiaArchitecture=Shared actor-critic networks, Seeds=5 random seeds2026.05899.5—