训练过程中 Tensorboard Log 中的 Rollout Entropy 和 Entropy 差距极大
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 8.5k
- Forks
- 1.3k
- Avg merge
- 5h 36m
- Merged PRs (30d)
- 22
Description
如题
训练过程中 rollout/entropy 和 train/entropy 之间差好几倍，是哪里计算出了问题么？
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reproducing the training run while monitoring the TensorBoard metrics rollout/entropy and train/entropy. Trace where each metric is calculated and logged, then compare their inputs and aggregation; done means the discrepancy is explained and any confirmed calculation problem is corrected.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning, observability
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100