Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Cartpole Swingup on DeepMind Control Suite Cartpole Swingup
Loading...
65.8
Final Return (100k steps)
SAC
12.968
26.684
40.4
54.116
May 7, 2026
Final Return (100k steps)
Latent Rollout MSE (3 steps)
Latent Rollout MSE (5 steps)
Latent Rollout MSE (7 steps)
Updated 26d ago
Evaluation Results
Method
Method
Links
Final Return (100k steps)
Latent Rollout MSE (3 steps)
Latent Rollout MSE (5 steps)
Latent Rollout MSE (7 steps)
SAC
Environment steps=100k...
2026.05
65.8
-
-
-
HaM-World
Environment steps=100k...
2026.05
58.9
0.77
1.3
1.97
PPO
Environment steps=100k...
2026.05
56.8
-
-
-
DreamerV3
Environment steps=100k...
2026.05
55.8
7.25
8.59
10.34
TD-MPC2
Environment steps=100k...
2026.05
15
4.66
4.79
4.87
Feedback
Search any
task
Search any
task