shoal 检验
play
详情
+84 −0 scienceslack.json 新增 查看文件
| @@ -0,0 +1,84 @@ | ||
| 1 | +{ | |
| 2 | + "description": "Kaggle Game Arena's Werewolf on kaggle-environments' own engine: seven players, two werewolves. Bring a Werewolf agent; it plays every role against the field.", | |
| 3 | + "image": "python:3.13-slim", | |
| 4 | + "cover": { | |
| 5 | + "file": "cover.png" | |
| 6 | + }, | |
| 7 | + "game": { | |
| 8 | + "shelf": "research", | |
| 9 | + "play": [ | |
| 10 | + "strategy" | |
| 11 | + ], | |
| 12 | + "mode": "live", | |
| 13 | + "players": "7", | |
| 14 | + "upstream": { | |
| 15 | + "name": "kaggle-environments", | |
| 16 | + "url": "https://github.com/Kaggle/kaggle-environments", | |
| 17 | + "license": "Apache-2.0", | |
| 18 | + "version": "1.33.0" | |
| 19 | + }, | |
| 20 | + "viewer": "viewer", | |
| 21 | + "room": "referee/room.sbatch", | |
| 22 | + "seats": [ | |
| 23 | + { | |
| 24 | + "id": "0", | |
| 25 | + "label": "1号" | |
| 26 | + }, | |
| 27 | + { | |
| 28 | + "id": "1", | |
| 29 | + "label": "2号" | |
| 30 | + }, | |
| 31 | + { | |
| 32 | + "id": "2", | |
| 33 | + "label": "3号" | |
| 34 | + }, | |
| 35 | + { | |
| 36 | + "id": "3", | |
| 37 | + "label": "4号" | |
| 38 | + }, | |
| 39 | + { | |
| 40 | + "id": "4", | |
| 41 | + "label": "5号" | |
| 42 | + }, | |
| 43 | + { | |
| 44 | + "id": "5", | |
| 45 | + "label": "6号" | |
| 46 | + }, | |
| 47 | + { | |
| 48 | + "id": "6", | |
| 49 | + "label": "7号" | |
| 50 | + } | |
| 51 | + ] | |
| 52 | + }, | |
| 53 | + "benchmark": { | |
| 54 | + "task": "Werewolf", | |
| 55 | + "metric": { | |
| 56 | + "name": "share of games won", | |
| 57 | + "better": "higher" | |
| 58 | + }, | |
| 59 | + "subtasks": "roles", | |
| 60 | + "aggregate": "mean", | |
| 61 | + "baseline": { | |
| 62 | + "name": "Starter (deterministic)", | |
| 63 | + "score": 0.642857, | |
| 64 | + "subtasks": { | |
| 65 | + "doctor": 0.5, | |
| 66 | + "seer": 0.833333, | |
| 67 | + "villager": 0.722222, | |
| 68 | + "werewolf": 0.5 | |
| 69 | + } | |
| 70 | + }, | |
| 71 | + "guardrails": [ | |
| 72 | + "Each move within 3 seconds", | |
| 73 | + "The agent is its own process and sees only what its role may see", | |
| 74 | + "No network: an agent calls no model here" | |
| 75 | + ], | |
| 76 | + "version": 1 | |
| 77 | + }, | |
| 78 | + "checks": { | |
| 79 | + "play": { | |
| 80 | + "path": "referee/check.sbatch", | |
| 81 | + "metrics": "metrics.json" | |
| 82 | + } | |
| 83 | + } | |
| 84 | +} | |