{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.001636868,0.0009111071,0.0007779338,0.001796706,0.000564991,0.001353317,0.00544934,0.0004367444,0.00003325375],"category_scores_gemma":[0.0004157481,0.000919461,0.0002350707,0.001229153,0.0004315659,0.0003598816,0.003062514,0.001722556,0.000121036],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0017276,"about_ca_system_score_gemma":0.001760539,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000278637,"about_ca_topic_score_gemma":0.00006404025,"domain_scores_codex":[0.9928839,0.00007094348,0.001188077,0.002149568,0.002358017,0.001349548],"domain_scores_gemma":[0.995662,0.0005555755,0.0005652204,0.002235,0.0005949849,0.0003871648],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006838112,0.00001351935,0.00002661621,0.00007601031,0.00001621374,0.00009706894,0.0003986454,0.8340173,0.00001828312,0.006545266,0.00005297731,0.1587313],"study_design_scores_gemma":[0.0003858225,0.0005181759,0.00002161886,0.0008690471,0.00001599437,0.00001669625,5.646411e-7,0.9559399,0.0001710026,0.004509286,0.03663498,0.0009169091],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000005736638,0.00009065038,0.9875162,0.001341121,0.002179397,0.001193034,0.000001194579,0.0004519412,0.007220767],"genre_scores_gemma":[0.04848931,0.00001874351,0.935384,0.00289025,0.000202774,0.00004573015,0.00002519891,0.00006842642,0.01287552],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1578144,"threshold_uncertainty_score":0.9999316,"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."}}