Update repo name to harpertoken-cartpole in all references
bniladridas
ed30aaa
Update README: remove broken links, update username to harpertoken, simplify model name to CartPole, remove noise from inference code
bniladridas
e93dd02
Update README.md
Niladri Das
Verified signature
d4a0976
Upload preview.mp4 with huggingface_hub
Niladri Das
Verified signature
f238a52
Upload cmaes_model.pth with huggingface_hub
Niladri Das
Verified signature
8a4b05b
Upload cmaes_model.npy with huggingface_hub
Niladri Das
Verified signature
ac6c36e
Update README.md
Niladri Das
Verified signature
d58baf8
Update README.md
Niladri Das
Verified signature
a9aa5e7
Update model card with implementation details and training results
Niladri Das
Verified signature
b4ca741
This update improves the model card documentation with:
- Added implementation code snippets showing the linear policy architecture
- Included CMAESAgent class structure and parameter details
- Updated training information with 100 generations and convergence behavior
- Clarified that training uses direct environment interaction (no pre-collected dataset)
- Added more accurate evaluation results (500.00 ±0.00 across all episodes)
- Improved usage examples with both high-level API and manual implementation options
- Updated repository links to GitHub and project website
Update README.md
Niladri Das
Verified signature
e41d7de
Upload README.md with huggingface_hub
Niladri Das
Verified signature
85a253c
Upload README.md with huggingface_hub
Niladri Das
Verified signature
f3e5485
Upload README.md with huggingface_hub
Niladri Das
Verified signature
a6b7af4
Upload README.md with huggingface_hub
Niladri Das
Verified signature
daf5d71
Upload README.md with huggingface_hub
Niladri Das
Verified signature
86d77a3
Upload README.md with huggingface_hub
Niladri Das
Verified signature
4da2759
Upload assets/training_convergence.png with huggingface_hub