Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Safe Reinforcement Learning on Safety Gym POINTGOAL1 (original)
Loading...
29
Utility Score
SEditor
12.36
16.68
21
25.32
Jan 28, 2022
Utility Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Utility Score
SEditor
Steps=2.5 x 10^7
2022.01
29
SEditor
Steps=1 x 10^7
2022.01
27
Stooke et al. (2020)
Steps=2.5 x 10^7
2022.01
26
SEditor
Steps=5 x 10^6
2022.01
24
Stooke et al. (2020)
Steps=1 x 10^7
2022.01
23
Stooke et al. (2020)
Steps=5 x 10^6
2022.01
22
TRPO-Lag
Steps=1 x 10^7
2022.01
17
TRPO-Lag
Steps=5 x 10^6
2022.01
16
PPO-Lag
Steps=5 x 10^6
2022.01
14
PPO-Lag
Steps=1 x 10^7
2022.01
13
Feedback
Search any
task
Search any
task