CoolFace
Apppublic

stargatek1/SSM-MetaRL-Unified

sourceHugging Facemitupdated 11mo agoView on Hugging Face
0likes
44 commits on main
368d8c911mo ago

Fix ExperienceBuffer.add() to accept RL experience tuple (obs, action, reward, next_obs, done)

stargatek1
4031f8f11mo ago

Remove 'with RSI' from Space description

stargatek1
b70abb811mo ago

Remove RSI file: cartpole_hybrid_real_model.pth

stargatek1
a8c4c3311mo ago

Remove RSI file: tests/test_rsi_integration.py

stargatek1
94fbfb111mo ago

Remove RSI file: MODEL_GENERATION_REPORT.md

stargatek1
68eb36d11mo ago

Remove RSI file: FIXES_SUMMARY.md

stargatek1
a092be611mo ago

Remove RSI file: RSI_DEPLOYMENT.md

stargatek1
7f49f7d11mo ago

Remove RSI file: recursive_self_improvement.py

stargatek1
cd75f2211mo ago

Fix imports - Use correct module paths (core.ssm, meta_rl.meta_maml, experience.experience_buffer)

stargatek1
87e818c11mo ago

Remove RSI - Clean version with only Meta-Training and Test-Time Adaptation

stargatek1
a79266211mo ago

Fix ALL errors: MetaMAML, adapters, config, env.step, action selection - ALL TABS WORKING

stargatek1
2dfe1b211mo ago

Fix Meta-Training and Test-Time Adaptation parameter errors

stargatek1
41bc2bf11mo ago

Upload train_improved_model.py with huggingface_hub

stargatek1
5964b4311mo ago

Upload tests/test_rsi_integration.py with huggingface_hub

stargatek1
957e4a611mo ago

Upload tests/test_rsi.py with huggingface_hub

stargatek1
8c8c42f11mo ago

Upload benchmarks/results/tables/benchmark_results.md with huggingface_hub

stargatek1
a7d28fd11mo ago

Upload benchmarks/results/plots/learning_curves.png with huggingface_hub

stargatek1
4e40c8f11mo ago

Upload benchmarks/results/plots/adaptation_comparison.png with huggingface_hub

stargatek1
fc7711711mo ago

Upload benchmarks/results/benchmark_results.json with huggingface_hub

stargatek1
64d837111mo ago

Upload benchmarks/cartpole_benchmark.py with huggingface_hub

stargatek1
7cc46b111mo ago

Upload FIXES_SUMMARY.md with huggingface_hub

stargatek1
b2bb48411mo ago

Upload models/cartpole_hybrid_real_model.pth with huggingface_hub

stargatek1
21974eb11mo ago

Upload recursive_self_improvement.py with huggingface_hub

stargatek1
5dcdcf911mo ago

Upload app.py with huggingface_hub

stargatek1
77351ae11mo ago

Upload app.py with huggingface_hub

stargatek1
92b08f811mo ago

Upload test_rsi_integration.py with huggingface_hub

stargatek1
c9ffaab11mo ago

Upload test_rsi.py with huggingface_hub

stargatek1
f90819411mo ago

Upload RSI_DEPLOYMENT.md with huggingface_hub

stargatek1
3a8202b11mo ago

Upload recursive_self_improvement.py with huggingface_hub

stargatek1
99bf7b311mo ago

Upload app.py with huggingface_hub

stargatek1
4a3aec711mo ago

Update README with enhanced documentation and tags

stargatek1
24ab95a11mo ago

Add training_log.txt - pre-trained model and updated app

stargatek1
2c1ac2311mo ago

Add verify_model.py - pre-trained model and updated app

stargatek1
21c115811mo ago

Add train_and_save_model.py - pre-trained model and updated app

stargatek1
806f38811mo ago

Add MODEL_GENERATION_REPORT.md - pre-trained model and updated app

stargatek1
ef0626f11mo ago

Add app.py - pre-trained model and updated app

stargatek1
8b51d3d11mo ago

Add cartpole_hybrid_real_model.pth - pre-trained model and updated app

stargatek1
bae81ad11mo ago

Complete SSM-MetaRL implementation with meta-training and test-time adaptation

stargatek1
f4655a811mo ago

Fix: Implement proper RL training with original SSM architecture

stargatek1
b2963c911mo ago

Fix: Replace with working REINFORCE implementation

stargatek1
bf8dd7011mo ago

Convert all Korean text to English in Gradio interface

stargatek1
c680fa111mo ago

Fix short_description length

stargatek1
69155dc11mo ago

Add original model files from GitHub repository

stargatek1
b1abfe711mo ago

initial commit

stargatek1