List your company

Continuous Control on DM Control reacher-hard

0.9705Average RewardMEOW
0.3212280.4897890.658350.826911Sep 24, 2025Nov 10, 2025Dec 27, 2025Feb 13, 2026Apr 1, 2026May 18, 2026Jul 5, 2026

Evaluation results

MethodLinks
MEOWTraining timesteps=1M, Seeds=52025.090.9705
SACTraining timesteps=1M, Seeds=52025.090.9637
FQLTraining timesteps=1M, Seeds=52025.090.9624
TD3Training timesteps=1M, Seeds=52025.090.9497
TD-MPC2Environment Steps=1M2026.070.9156
RC-SACtraining steps=50 [k], seeds=3, w_target=0.52026.030.91
SACtraining steps=50 [k], seeds=3, w_target=0.52026.030.9
MIST-WMEnvironment Steps=1M2026.070.8716
Factored DreamerEnvironment Steps=1M2026.070.8693
RC-TD3training steps=50 [k], seeds=3, w_target=0.52026.030.82
TD3training steps=50 [k], seeds=3, w_target=0.52026.030.76
DDPGTraining timesteps=1M, Seeds=52025.090.758
Dreamer-v3Environment Steps=1M2026.070.7024
DINO-WMEnvironment Steps=1M2026.070.3462