{"id":"W4411745406","doi":"10.1007/978-3-031-95976-9_9","title":"Reinforcement Learning-Based Heuristics to Guide Domain-Independent Dynamic Programming","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"The King's University; Canada Research Chairs; University of Toronto","funders":"","keywords":"Computer science; Reinforcement learning; Heuristics; Domain (mathematical analysis); Artificial intelligence; Dynamic programming; Machine learning; Algorithm; Operating system; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009295209,0.001104534,0.00110207,0.0006993745,0.000472762,0.001011803,0.001578055,0.001021186,0.005782478],"category_scores_gemma":[0.004490439,0.0006857959,0.0006152461,0.0006547818,0.0009318467,0.001185307,0.001479793,0.002117861,0.000957662],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009921427,"about_ca_system_score_gemma":0.001406933,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003800365,"about_ca_topic_score_gemma":0.006524329,"domain_scores_codex":[0.9996778,0.0001122583,0.00001787799,0.00007133732,0.00007107798,0.00004973892],"domain_scores_gemma":[0.998398,0.001159345,0.0000812088,0.0001149228,0.0001663665,0.00008020118],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00008268053,0.00008783085,0.0002681454,0.00009151831,0.00002881468,0.00005081471,0.00008832467,0.8377675,0.001480383,0.04274802,0.003605589,0.1137004],"study_design_scores_gemma":[0.00001625928,0.00001498558,0.00002770038,0.00001251568,0.000004285233,0.000007086534,0.000006724551,0.9847809,0.0003591276,0.01402602,0.0007397596,0.000004614154],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006435506,0.0001838458,0.9874263,0.00009699191,0.00004580844,0.00006026386,0.00003663095,0.0006092026,0.005105451],"genre_scores_gemma":[0.4046748,0.0003349686,0.5883189,0.0001791968,0.00005659522,0.0003260112,0.0001997038,0.0004120932,0.005497781],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005782478,"threshold_uncertainty_score":0.01934433,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009434525304242686,"score_gpt":0.2577204471215944,"score_spread":0.2482859218173517,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}