Flattened observations disagree with explicitly declared task specifications
還沒有人認領這個 Issue。
評估
- 難度
- 3/5
- 預估耗時
- 1-2 天
- 新手友好度
- 74/100
- Issue 類型
- 缺陷
- 描述清晰度
- 基本清楚
- 活躍度
- 活躍
- 技術堆疊
- numpy, python
研究方向
Start at control.Environment.observation_spec and compare the explicit-spec path with the existing fallback flattening path used when no specification is declared. Check that flat_observation preserves shapes and NumPy dtype promotion without materializing observations or calling get_observation, while leaving the caller's spec and mapping type unchanged. Run the regression against reset and step behavior to confirm the declared and inferred paths agree.
由索引模型根據 Issue 內容生成。
描述
Reproduction
On current main, an environment using flat_observation=True flattens the values returned by reset and step, but returns an unflattened specification when the task implements observation_spec.
For example, a task declaring a float32 position array of shape (2,) and an int32 scalar mode produces one float64 observations array of shape (3,). Environment.observation_spec() instead returns the original two specifications.
The fallback path for tasks without an explicit specification already flattens correctly. Agents that allocate or validate observations from the environment specification therefore behave differently depending on whether the task supplies its own spec.
Expected behavior
Flatten the declared shapes and apply NumPy's concatenation dtype promotion when flattening is enabled, without materializing observation arrays or calling get_observation. Preserve the caller's spec, mapping type, normal unflattened behavior, and the existing inference path.
Reproduced with actual control.Environment calls and a small native MuJoCo task. The new regression fails on current main at a04e3e4cf56c12117d2294bb090f9acec21e5c67; no renderer, trained policies or external service is required.
- 主要語言
- Python
- 星號
- 4.7k
- 分支
- 765
- PR 合併指標
- 30 天內沒有已合併 PR
環境準備
從這裡開始
- 先讀完整個 Issue,再讀專案的貢獻指南。
- 在 Issue 下留言說明你要接手 —— 這能避免兩個人做同樣的事。
- Fork 儲存庫,在一個分支上完成修改。
- 送出 Pull Request,並在描述裡引用這個 Issue 編號。
google-deepmind/dm_control 的其他 Issue
-
難度 2/5 1-3 小時 新手友好度 85/100
google-deepmind/dm_control#559 ·
-
難度 3/5 1-2 天 新手友好度 75/100
google-deepmind/dm_control#560 ·
-
難度 3/5 1-2 天 新手友好度 76/100
google-deepmind/dm_control#552 ·
-
難度 3/5 1-2 天 新手友好度 45/100
google-deepmind/dm_control#540 · 1 則留言 ·
-
難度 3/5 1-2 天 新手友好度 55/100
google-deepmind/dm_control#537 · 1 則留言 ·
查看 google-deepmind/dm_control 的全部 Issue
相似的 Issue
-
customer-reported
難度 2/5 1-3 小時 新手友好度 68/100
Azure/azure-cli#34150 · 1 則留言 ·
維護者通常 1 天內回覆
-
community-request
難度 1/5 1 小時以內 新手友好度 95/100
NVIDIA-NeMo/Curator#2464 · 1 則留言 ·
維護者通常 1 天內回覆
-
難度 2/5 1-3 小時 新手友好度 88/100
WeblateOrg/translation-finder#1099 ·
維護者通常 1 天內回覆
-
難度 2/5 1-3 小時 新手友好度 68/100
trezor/trezor-firmware#7997 ·
維護者通常 2 天內回覆
-
難度 2/5 1-3 小時 新手友好度 88/100
維護者通常 1 天內回覆