Hugging Face
Search models, datasets, users...
Ctrl K
Models
Datasets
Spaces
Buckets
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
HarleyCooper
/
grid-policy-mlp-self-improved
Like
0
Reinforcement Learning
Safetensors
HarleyCooper/grid-policy-mlp-self-improved-trajectories
grid-policy-mlp
failure-driven-learning
gradient
breakout
failure-is-all-you-need
License:
mit
Model card
Files
Files and versions
xet
Community
Copy to bucket
main
grid-policy-mlp-self-improved
202 kB
Ctrl+K
Ctrl+K
1 contributor
History:
3 commits
HarleyCooper
Explain failure-driven training, measured improvements, replay gates, and limitations
44c577d
verified
13 days ago
.gitattributes
Safe
1.52 kB
initial commit
13 days ago
LICENSE
Safe
1.27 kB
Publish audited gradient self-improvement from original PPO base
13 days ago
README.md
Safe
18.6 kB
Explain failure-driven training, measured improvements, replay gates, and limitations
13 days ago
audit.json
Safe
4.19 kB
Publish audited gradient self-improvement from original PPO base
13 days ago
config.json
Safe
603 Bytes
Publish audited gradient self-improvement from original PPO base
13 days ago
inference.py
Safe
5.42 kB
Publish audited gradient self-improvement from original PPO base
13 days ago
initial_baseline.npz
39.7 kB
xet
Publish audited gradient self-improvement from original PPO base
13 days ago
model.py
Safe
1.24 kB
Publish audited gradient self-improvement from original PPO base
13 days ago
model.safetensors
69.4 kB
xet
Publish audited gradient self-improvement from original PPO base
13 days ago
plan.json
Safe
10.5 kB
Publish audited gradient self-improvement from original PPO base
13 days ago
policy_weights.npz
48.9 kB
xet
Publish audited gradient self-improvement from original PPO base
13 days ago
summary.json
Safe
846 Bytes
Publish audited gradient self-improvement from original PPO base
13 days ago