Spaces:

sh4shv4t
/

Parlay

Paused

Parlay / tests

52.2 kB

Ctrl+K

1 contributor

Add pre-training audit scripts, OpenEnv manifest, and tune Parlay training/env (GRPO 1.5B default, min-reward filters, weighted data gen, hiring ZOPA+drift, veteran/opponent prompts, Docker/docs)

df724f2 about 1 month ago

__init__.py

25 Bytes
feat: project setup about 2 months ago
test_episode_filters.py

2.41 kB
feat: streamline parlay for demo mode and add spectator negotiation mechanics about 1 month ago
test_game_theory.py

4.85 kB
feat: project setup about 2 months ago
test_grader.py

5.9 kB
feat: streamline parlay for demo mode and add spectator negotiation mechanics about 1 month ago
test_keyless.py

15.5 kB
Add pre-training audit scripts, OpenEnv manifest, and tune Parlay training/env (GRPO 1.5B default, min-reward filters, weighted data gen, hiring ZOPA+drift, veteran/opponent prompts, Docker/docs) about 1 month ago
test_reward.py

1.1 kB
feat: project setup about 2 months ago
test_scenarios.py

1.89 kB
feat: streamline parlay for demo mode and add spectator negotiation mechanics about 1 month ago
test_tactical_cards.py

7.89 kB
feat: flash-lite for data-gen and flash for UI; remove training page; card tests; --quiet data gen; data/ inspect path; random baseline; GRPO env wrapper; reward fixes (buyer ZOPA, ToM signals); drift + Brier metrics; Bayesian ToM module about 1 month ago
test_tom.py

3.11 kB
feat: streamline parlay for demo mode and add spectator negotiation mechanics about 1 month ago
test_training_pipeline.py

9.43 kB
feat: split Gemini 2.5 Flash (demo) and Flash-Lite (data), SFT threshold 0.3, favicon + check_gemini about 1 month ago