Pacman
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Backdoor Attack on Reinforcement Learning | Pacman Discrete (evaluation) | Backdoor Rate (BR)628.7 | 5 | |
| Reinforcement Learning | Pacman | Average Reward10,000 | 4 | |
| Value Iteration | pacman | Iterations2 | 2 | |
| MDP Policy Reachability | Pacman | State Coverage47.2 | 1 |
Showing 4 of 4 rows