Spaces:

chane335
/

permanence-training

Paused

App Files Files Community

permanence-training / docs

251 kB

Ctrl+K

Ctrl+K

1 contributor

History: 5 commits

chane335's picture

PERMANENCE: reversibility-aware RL environment for training LLM agents

8f27137 verified about 1 month ago

ARCHITECTURE.md

10.4 kB
PERMANENCE: reversibility-aware RL environment for training LLM agents about 1 month ago
BLOG_POST.md

11.4 kB
PERMANENCE: reversibility-aware RL environment for training LLM agents about 1 month ago
BLOG_POST_TEMPLATE.md

8.48 kB
Upload folder using huggingface_hub about 1 month ago
IMPLEMENTATION_CONTEXT.md

995 Bytes
Upload folder using huggingface_hub about 1 month ago
Judging_criterion.txt

11.6 kB
Upload folder using huggingface_hub about 1 month ago
METHODS.md

9.15 kB
PERMANENCE: reversibility-aware RL environment for training LLM agents about 1 month ago
PART1_DEVELOPMENT_TRAINING_CHECKLIST.md

10.8 kB
Run 4: tech-only curriculum, 3B model, integrated deploy task about 1 month ago
PART1_MASTER_CHECKLIST.md

7.08 kB
Upload folder using huggingface_hub about 1 month ago
PART1_QUICK_SUMMARY.md

4.75 kB
Upload folder using huggingface_hub about 1 month ago
PERMANENCE_AGENT_CONTEXT.md

22.4 kB
Upload folder using huggingface_hub about 1 month ago
PERMANENCE_MASTER_SPEC.md

88.1 kB
Upload folder using huggingface_hub about 1 month ago
PERMANENCE_PROJECT_DESCRIPTION.md

12.1 kB
Upload folder using huggingface_hub about 1 month ago
PROJECT_EXPLAINED.txt

31.8 kB
Sync: new curriculum, 6 tasks, composable rubric, latent dynamics about 1 month ago
RESULTS.md

6.7 kB
PERMANENCE: reversibility-aware RL environment for training LLM agents about 1 month ago
RUN7_RUN8_SECOND_OPINION.txt

15.5 kB
Run 6.1: env precondition fix (destructive DB ops on missing tables short-circuit) about 1 month ago