Reinforcement Learning on RoomEnv-v1
Metric: final agent reward (higher is better)
LeaderboardDataset
Loading chart...
Results
Submit a result| # | Model↕ | final agent reward▼ | Augmentations | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | HumemAI-v0-capacity=32-semantic-pretrained | 116.5 | No | A Machine with Short-Term, Episodic, and Semanti... | 2022-12-05 | Code |
| 2 | HumemAI-v0-capacity=32-semantic-scratch | 109 | No | A Machine with Short-Term, Episodic, and Semanti... | 2022-12-05 | Code |