SELA #1514
Merged
SELA #1514
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
2. correct import
2. fix import
2. fix bug
2. 修改prompt，让predictions.csv生成的格式与原gt格式一样
2. Dummy CustomExperimenter
add experimenter See merge request agents/exp_optimizer!1
2. fix duration
Experimenter See merge request agents/exp_optimizer!2
fix import See merge request agents/exp_optimizer!3
garylin2099
temporarily deployed
to
pre-commit
GitHub Actions
Inactive
garylin2099
had a problem deploying
to
unittest
GitHub Actions
Failure
garylin2099
temporarily deployed
to
pre-commit
GitHub Actions
Inactive
garylin2099
commented
Oct 30, 2024
garylin2099
commented
Oct 30, 2024
garylin2099
commented
Oct 30, 2024
garylin2099
commented
Oct 30, 2024
garylin2099
had a problem deploying
to
pre-commit
GitHub Actions
Failure
garylin2099
had a problem deploying
to
unittest
GitHub Actions
Failure
|
LGTM |
garylin2099
had a problem deploying
to
unittest
GitHub Actions
Failure
garylin2099
temporarily deployed
to
pre-commit
GitHub Actions
Inactive
garylin2099
temporarily deployed
to
pre-commit
GitHub Actions
Inactive
geekan
reviewed
Oct 30, 2024
| Official implementation for paper [SELA: Tree-Search Enhanced LLM Agents for Automated Machine Learning](https://arxiv.org/abs/2410.17238). | ||
|
|
||
|
|
||
| SELA is an innovative system that enhances Automated Machine Learning (AutoML) by integrating Monte Carlo Tree Search (MCTS) with LLM-based agents. Traditional AutoML methods often generate low-diversity and suboptimal code, limiting their effectiveness in model selection and ensembling. SELA addresses these challenges by representing pipeline configurations as trees, enabling agents to intelligently explore the solution space and iteratively refine their strategies based on experimental feedback. |
There was a problem hiding this comment.
solution space in paper abstract, i think it's okay if we are talking at a high level that the agent is searching for a solution or pipeline
| python run_experiment.py --exp_mode rs --task titanic --rs_mode set | ||
| ``` | ||
|
|
||
| ## 4. Citation |
There was a problem hiding this comment.
Also added to the outermost README of MetaGPT
| datasets_dir = config["datasets_dir"] | ||
| if dataset_name in config["datasets"]: | ||
| dataset = config["datasets"][dataset_name] | ||
| data_path = os.path.join(datasets_dir, dataset["dataset"]) |
There was a problem hiding this comment.
I noticed that a lot of os.path is used. Can you use pathlib instead?
| additional_instruction=additional_instruction, | ||
| data_info_path=data_info_path, | ||
| ) | ||
| print(user_requirement) |
There was a problem hiding this comment.
Can all prints be changed to use metagpt logger?
geekan
approved these changes
Oct 31, 2024
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.
No description provided.