Upload folder using huggingface_hub

fix: batch normalization, EMA baseline, investigation bonuses, entity regex

fix: final audit — orchestrator scores, KL direction, grader typology alias

fix: terminal actions skip grade_step to prevent reward double-count

feat: self-play AML simulator — clean scenarios, reward composition, OS metrics

chore: Finalize Phase 1-3 upgrades (Memex UI, 3D Globe, Adversarial Training, Reward Caps)

feat: Phase 3 FinCEN 4-pillar expansion — industrial-grade AML environment

feat: add OpenEnv server wrapper, HF Spaces Dockerfile, fix upload bloat

fix: remote repo sync

feature: further improvements

feature: initial AML implementation

resolved merge conflict

resolved merge conflict

Final Grand Finale Polish - Agent & README Upgrade

fix: resolve remaining merge conflict markers

chore: First iteration of OpenEnv AML Environment ready for submission~

fix: make reset request body optional to fix 422 grading error

resolved merge conflict