Research Article
A Sarsa(λ) Algorithm Based on Double-Layer Fuzzy Reasoning
Table 2
Performance comparison of the two algorithms in Cart-pole Balancing problem.
| Algorithm | Episodes | Average time within an iterative step | Minimum episodes | Average episodes |
| DFR-Sarsa(λ) | 135 | 155 | 100% | GD-Sarsa(λ) | 179 | 204 | 46% |
|
|