| { |
| "no_change": { |
| "mode": "REGIMEN_OPT", |
| "action_type": "KEEP_REGIMEN", |
| "target_drug": null, |
| "replacement_drug": null, |
| "dose_bucket": "NA", |
| "taper_days": null, |
| "monitoring_plan": null, |
| "evidence_query": null, |
| "new_drug_name": null, |
| "candidate_components": [], |
| "candidate_id": "cand_01", |
| "confidence": 0.8, |
| "rationale_brief": "Baseline no-change policy." |
| }, |
| "rules_only": { |
| "mode": "REGIMEN_OPT", |
| "action_type": "SUBSTITUTE_WITHIN_CLASS", |
| "target_drug": "opioid_like", |
| "replacement_drug": "non_opioid_analgesic", |
| "dose_bucket": "NA", |
| "taper_days": null, |
| "monitoring_plan": null, |
| "evidence_query": null, |
| "new_drug_name": null, |
| "candidate_components": [], |
| "candidate_id": "cand_04", |
| "confidence": 0.75, |
| "rationale_brief": "Rules-only selected top legal candidate." |
| }, |
| "greedy": { |
| "mode": "REGIMEN_OPT", |
| "action_type": "SUBSTITUTE_WITHIN_CLASS", |
| "target_drug": "opioid_like", |
| "replacement_drug": "non_opioid_analgesic", |
| "dose_bucket": "NA", |
| "taper_days": null, |
| "monitoring_plan": null, |
| "evidence_query": null, |
| "new_drug_name": null, |
| "candidate_components": [], |
| "candidate_id": "cand_04", |
| "confidence": 0.72, |
| "rationale_brief": "Greedy safety/burden improvement baseline." |
| }, |
| "contextual_bandit": { |
| "mode": "REGIMEN_OPT", |
| "action_type": "SUBSTITUTE_WITHIN_CLASS", |
| "target_drug": "opioid_like", |
| "replacement_drug": "non_opioid_analgesic", |
| "dose_bucket": "NA", |
| "taper_days": null, |
| "monitoring_plan": null, |
| "evidence_query": null, |
| "new_drug_name": null, |
| "candidate_components": [], |
| "candidate_id": "cand_04", |
| "confidence": 0.68, |
| "rationale_brief": "Contextual bandit selected candidate." |
| }, |
| "contextual_bandit_topk": [ |
| { |
| "candidate_id": "cand_09", |
| "score": 1.1532307878304324, |
| "exploration_bonus": 1.1532307878304324, |
| "algorithm": "linucb" |
| }, |
| { |
| "candidate_id": "cand_10", |
| "score": 1.1489735636645433, |
| "exploration_bonus": 1.1489735636645433, |
| "algorithm": "linucb" |
| }, |
| { |
| "candidate_id": "cand_08", |
| "score": 1.1447401451857973, |
| "exploration_bonus": 1.1447401451857973, |
| "algorithm": "linucb" |
| } |
| ], |
| "beam_search": { |
| "mode": "REGIMEN_OPT", |
| "action_type": "SUBSTITUTE_WITHIN_CLASS", |
| "target_drug": "opioid_like", |
| "replacement_drug": "non_opioid_analgesic", |
| "dose_bucket": "NA", |
| "taper_days": null, |
| "monitoring_plan": null, |
| "evidence_query": null, |
| "new_drug_name": null, |
| "candidate_components": [], |
| "candidate_id": "cand_04", |
| "confidence": 0.74, |
| "rationale_brief": "Beam-search(3) top candidate." |
| }, |
| "baseline_policy": "no_change_candidate", |
| "episodes": 8, |
| "avg_reward": 0.747, |
| "legality_rate": 1.0, |
| "success_rate": 0.0, |
| "policy_stack_ablations": { |
| "bandit-only": { |
| "avg_reward": 0.7616666666666667, |
| "legality_rate": 1.0, |
| "steps": 3.0 |
| }, |
| "llm-only": { |
| "avg_reward": 0.7753333333333333, |
| "legality_rate": 1.0, |
| "steps": 3.0 |
| }, |
| "llm+bandit": { |
| "avg_reward": 0.7753333333333333, |
| "legality_rate": 1.0, |
| "steps": 3.0 |
| } |
| } |
| } |
