feature(pu): add UniZero algo. and related configs/utils/envs/models #232
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Collaborator
puyuan1996
commented
Jun 11, 2024
•
puyuan1996
commented
- Add UniZero algo. and related configs/utils/envs/models
- Our arxiv paper is on UniZero: Generalized and Efficient Planning with Scalable World Models.
… all, use batchsize 256 for tokenizer
PaParaZz1
requested changes
Jul 1, 2024
zjowowen
reviewed
Jul 2, 2024
zjowowen
reviewed
Jul 2, 2024
PaParaZz1
requested changes
Jul 3, 2024
PaParaZz1
requested changes
Jul 3, 2024
lzero/entry/train_unizero.py
Outdated
| if cfg.policy.use_priority: | ||
| replay_buffer.update_priority(train_data, log_vars[0]['value_priority_orig']) | ||
|
|
||
| # Clear caches and precompute positional embedding matrices |
There was a problem hiding this comment.
move these part to the __del__ method of world_model
There was a problem hiding this comment.
因为是每个train epoch都需要调用一次，因为我在unizero中新建了一个recompute_pos_emb_diff_and_clear_cache() methid哈
| """ | ||
| assert embed_dim % num_heads == 0 | ||
| self._n, self._cache, self._size = num_samples, None, None | ||
| self._reset = lambda n: torch.empty(n, num_heads, max_tokens, embed_dim // num_heads, |
There was a problem hiding this comment.
why use lambda function here, rather than directly writing the implementation in reset method
There was a problem hiding this comment.
这里使用 lambda function，可以避免很多参数的传递，效果是类似的
puyuan1996
added
enhancement
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.