Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Goal-conditioned navigation on MiniGrid 8x8 RGB image input (test)
Loading...
0.43
Clean Reward
TDRT-PPO
0.3676
0.3838
0.4
0.4162
Jun 6, 2024
Clean Reward
Attack Reward (SA-RL)
Attack Reward (PA-AD)
Attack Reward (BIA-ILfD, ours)
Attack Reward (Avg)
Updated 4d ago
Evaluation Results
Method
Method
Links
Clean Reward
Attack Reward (SA-RL)
Attack Reward (PA-AD)
Attack Reward (BIA-ILfD, ours)
Attack Reward (Avg)
TDRT-PPO
Target Reward=0.96 ± 0
2024.06
0.43
0.32
0.58
0.29
0.4
PPO
Target Reward=0.96 ± 0...
2024.06
0.37
0.5
0.92
0.48
0.63
Feedback
Search any
task
Search any
task