Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Reinforcement Learning on Spring Pendulum
Loading...
182.4221
Episode Reward
RPO-SAC
-6.402588
42.619206
91.641
140.662794
Oct 14, 2023
Episode Reward
Max Instantaneous Inequality Violation
Max Instantaneous Equality Violation
Max Episode Inequality Violation
Max Episode Equality Violation
Updated 4d ago
Evaluation Results
Method
Method
Links
Episode Reward
Max Instantaneous Inequality Violation
Max Instantaneous Equality Violation
Max Episode Inequality Violation
Max Episode Equality Violation
RPO-SAC
2023.10
182.4221
0
0
0
0
RPO-DDPG
2023.10
175.1558
0
0
0
0
SAC-L
type=abridged version
2023.10
149.6762
0
0.0078
0
0.0837
DDPG-L
type=abridged version
2023.10
76.4383
0
0.3805
0
1.0905
CPO
2023.10
15.4687
0
0.7274
0
1.9064
Safety Layer
2023.10
1.1155
6.0975
3.9134
36.9545
25.2101
CUP
2023.10
0.8599
0
9.5898
0
16.3114
Feedback
Search any
task
Search any
task
