decider_config.json

{"temperature": 1.3, "temperature_schema_first": 1.18, "neutralize_none": false, "version": "v10", "base": "Qwen/Qwen3.5-2B-Base", "max_options": 255, "max_state_tokens": 32768, "schema_first": false, "schema_first_trained": true, "isolated_levels": true, "release_date": "2026-09-19", "parent": "decider-2b v8 (Mapika/decider-2b, tag v8)", "stage": "calibration-aware RL, 384 steps, outcome rewards from live MiniWoB++ click tasks and exact games, KL retention to v8 (docs/RL.md)"}