GridWorld
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
GridWorld
8Iterations (gamma=0.9)
3
GridWorld p = 0.4
0.336Mean Execution Time (s)
2
GridWorld p = 0.9
0.261Mean Execution Time (s)
2
GridWorld p = 0.4 Catastrophic Path
-698Lowest Cumulative Reward
2
GridWorld (p = 0.4) - Almost Catastrophic
14Lowest Cumulative Reward
2
GridWorld p = 0.4 Slightly Suboptimal Path
19Lowest Cumulative Reward
2
GridWorld (p = 0.9) Catastrophic Path
-698Lowest Cumulative Reward
2
GridWorld (p = 0.9) - Almost Catastrophic
-697Cumulative Reward (Lowest)
2
GridWorld (p = 0.9) Slightly Suboptimal Path
-495Lowest Cumulative Reward
2
GridWorld p = 0.4
230Worst-Case Counterfactual V(s0)
2
GridWorld p = 0.9
346Avg Worst-Case Counterfactual V(s0)
2
GridWorld 5x5
0.008PBVI orig Time (s)
1
GridWorld 3x3
0.003PBVI Time (Original) (s)
1