Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
Hana-ame
/
maze-transformer
like
0
Reinforcement Learning
PyTorch
grpo
maze-navigation
pomdp
transformer
tiny-model
quantization
License:
mit
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
maze-transformer
264 kB
Ctrl+K
Ctrl+K
2 contributors
History:
40 commits
Hana-ame
Merge remote-tracking branch 'origin/main'
6ea546e
about 9 hours ago
archive
docs(excel): record changelog and events into EXPERIMENTS_ALL.xlsx
1 day ago
configs
feat(excel): sync single-sheet EXPERIMENTS_ALL.xlsx and test_objective configs
about 24 hours ago
experiments
Update maze transformer: modified RL components and added experiment configs
1 day ago
maze_transformer
Merge remote-tracking branch 'origin/main'
about 9 hours ago
tools
tune: 调参空间扩展至 45 参数 — 补预热方式/损失缩放/ZeRO/激活重计算/FSDP,层数与宽度量级放大;格式=参数:候选值枚举
2 days ago
.gitattributes
Safe
2.27 kB
docs: DOCS_ALL.xlsx 全量 39 份 (classic upload)
2 days ago
.gitignore
Safe
736 Bytes
docs: README 补 DOCS_ALL.xlsx 全量 39 份说明;.gitignore 注释更新(xlsx 走 HF LFS,本地 --skip-worktree)
2 days ago
Colab_Run_Maze_Transformer.ipynb
8.73 kB
feat(maze): add --config support, Colab notebook, INT8 quantization module, and updated experiments excel
1 day ago
EXPERIMENTS_ALL.xlsx
9.63 kB
chore(excel): update EXPERIMENTS_ALL.xlsx format and sync
about 23 hours ago
LICENSE
Safe
1.06 kB
feat: reactive 2D-maze navigation transformer (MazeGPT)
3 days ago
README.md
6.02 kB
docs: 完善中文文档与 DIY 操作手册
about 23 hours ago
pyproject.toml
Safe
1.14 kB
feat: reactive 2D-maze navigation transformer (MazeGPT)
3 days ago
requirements.txt
Safe
22 Bytes
feat: reactive 2D-maze navigation transformer (MazeGPT)
3 days ago
use_model.sh
Safe
1.55 kB
feat: reactive 2D-maze navigation transformer (MazeGPT)
3 days ago