Commonsense Rl On Commonsense Rl
평가 지표
Avg #Steps
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | Avg #Steps | Paper Title | Repository |
|---|---|---|---|
| Human | 15.00 ± 3.29 | Text-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Baselines | |
| Optimal | 15.00 ± 2.00 | Text-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Baselines | |
| KG-A2C | 49.36 ± 7.50 | Text-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Baselines | |
| TNC-A2C | 43.27 ± 0.70 | Text-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Baselines | |
| LSTM-A2C | 49.21 ± 0.58 | Text-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Baselines |
0 of 5 row(s) selected.