List your company

ResearchFormerly WizWand

grid case

Benchmarks

TaskDatasetSOTA resultTrendResults

Reinforcement Learning Convergence

30x30 grid case

64,567.3Average Q-values

12

Reinforcement Learning Convergence

grid case 25x25

19,693.2Average Q-values

12

Reinforcement Learning Convergence

grid case 20x20

55,113.2Average Q-values

12

Reinforcement Learning Convergence

grid case 15x15

6,625.1Average Q-values

12

Reinforcement Learning Convergence

grid case 10x10

3,521.4Average Q-values

12