{"id":"W4411745413","doi":"10.1007/978-3-031-95976-9_16","title":"Shaping Reward Signals in Reinforcement Learning Using Constraint 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":"Polytechnique Montréal","funders":"","keywords":"Reinforcement learning; Computer science; Constraint (computer-aided design); Artificial intelligence; Constraint programming; Reinforcement; Constraint satisfaction; Mathematical optimization; Psychology; Mathematics; Stochastic programming","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":[0.001029102,0.0008422514,0.00084931,0.0002900237,0.0003481164,0.001242381,0.001508322,0.001066791,0.005593244],"category_scores_gemma":[0.00378371,0.0006050714,0.0005370636,0.0009044748,0.001492007,0.001347826,0.001112213,0.002736946,0.000651271],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001102124,"about_ca_system_score_gemma":0.0009095711,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00348998,"about_ca_topic_score_gemma":0.003306476,"domain_scores_codex":[0.9994654,0.0002165346,0.00002375319,0.00009041669,0.0001558925,0.00004816166],"domain_scores_gemma":[0.9982498,0.001419298,0.00007867788,0.00008096571,0.0001259782,0.0000451897],"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":[0.0000721411,0.00005123802,0.0001194995,0.0001700652,0.00003288506,0.00004757733,0.00006411762,0.7418224,0.002078838,0.1536458,0.002582769,0.0993127],"study_design_scores_gemma":[0.0000107523,0.00001654413,0.00002931238,0.00001733542,0.000005440295,0.00001077457,0.000005766826,0.943216,0.0007287978,0.05421097,0.001739993,0.000008443227],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003616096,0.0004448701,0.985971,0.0001522894,0.00003962328,0.00003051504,0.00002522022,0.0001615105,0.0095588],"genre_scores_gemma":[0.4114234,0.001417951,0.5685252,0.0002580405,0.0001054174,0.0003896684,0.0001247623,0.0003480548,0.01740753],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005593244,"threshold_uncertainty_score":0.01871127,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03778212600561777,"score_gpt":0.2821269068680285,"score_spread":0.2443447808624108,"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."}}