Spaces:
Running
Running
Commit History
-
feat: implement Unsloth GRPO training script with diverse reward functions and logging
d2449aa -
fix: update training script with seed variation, fix reward normalization, regenerate training curves showing 0.52->0.67 improvement
bdc9954 -
feat: add scripts/full_demo.py — unified 10-step demo proving all 4 hackathon themes operational
5636c9d -
fix: training reward uses 8-step rollout + /grade for genuine episode-level signal
c70e17d -
feat: commit training evidence, update README with real scores, add demo scripts
8204dc0 -
feat: add baseline evaluation tools and demo scripts for RL performance comparison
c395f6a -
feat: add GridMind GRPO training notebook using Unsloth and HF TRL
bdadba1
-
Add Task 4 instruction following, Curriculum Manager for self-improvement, and world modeling simulation
- Add Task 4: Instruction Following - agent parses objective card and plans actions - Add CurriculumManager: auto-advances task difficulty when reward thresholds met - Add /simulate endpoint: world modeling to predict action outcomes before committing - Fix: add _default_action method to LLMAgent class (was defined outside) - Enable simulation warnings when predicted reward falls below running average0af208b -
Add GridMind GRPO training notebook for Colab
fd2ceda
-
feat: add OpenEnv submission validator script to check HF Space status and Docker build
e82aa27