Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Continuous Control on DM Control reacher-hard
Loading...
0.9705
Average Reward
MEOW
0.321228
0.489789
0.65835
0.826911
Sep 24, 2025
Nov 10, 2025
Dec 27, 2025
Feb 13, 2026
Apr 1, 2026
May 18, 2026
Jul 5, 2026
Average Reward
Updated 19d ago
Evaluation Results
Method
Method
Links
Average Reward
MEOW
Training timesteps=1M,...
2025.09
0.9705
SAC
Training timesteps=1M,...
2025.09
0.9637
FQL
Training timesteps=1M,...
2025.09
0.9624
TD3
Training timesteps=1M,...
2025.09
0.9497
TD-MPC2
Environment Steps=1M
2026.07
0.9156
RC-SAC
training steps=50 [k],...
2026.03
0.91
SAC
training steps=50 [k],...
2026.03
0.9
MIST-WM
Environment Steps=1M
2026.07
0.8716
Factored Dreamer
Environment Steps=1M
2026.07
0.8693
RC-TD3
training steps=50 [k],...
2026.03
0.82
TD3
training steps=50 [k],...
2026.03
0.76
DDPG
Training timesteps=1M,...
2025.09
0.758
Dreamer-v3
Environment Steps=1M
2026.07
0.7024
DINO-WM
Environment Steps=1M
2026.07
0.3462
Feedback
Search any
task
Search any
task