Reinforcement Learning on CartPole v1 (test)
500Total Reward
Qualitatively measured policy discrepancy w/ β
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| 500 | 1,157.2 | ||
| 500 | 1,157.2 | ||
| 500 | 1,157.2 | ||
| 500 | 106.8 | ||
| 500 | 53.4 | ||
| 500 | 35.6 | ||
| 500 | 21.1 | ||
| 499.9 | 1,157.2 | ||
2020.12 | 499.9 | 1,157.2 | |
| 499.4 | 1,157.2 | ||
2020.12 | 498.7 | 1,157.2 | |
2020.12 | 496.7 | 1,157.2 | |
| 494.9 | 1,157.2 | ||
2020.12 | 494.7 | 1,157.2 | |
| 493.3 | 1,157.2 | ||
| 493.2 | 1,157.2 | ||
2020.12 | 489.9 | 1,157.2 | |
2020.12 | 484.3 | 1,157.2 | |
2020.12 | 461.1 | 1,157.2 | |
| 388.76 | 89.2 | ||
2020.12 | 327.3 | 1,157.2 | |
| 321 | 70,786.2 | ||
| 136.75 | 8,090.4 | ||
| 113.52 | 8,090.4 | ||
2020.12 | 98.33 | 5,170,174.8 |