{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002206792,0.0007406882,0.0008210578,0.002043452,0.0004014143,0.001155282,0.003250184,0.000431616,0.00003297044],"category_scores_gemma":[0.000379939,0.0007764628,0.0001582001,0.001318217,0.0007034856,0.0008097597,0.002497962,0.002050997,0.00001711087],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001188607,"about_ca_system_score_gemma":0.00137753,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005874086,"about_ca_topic_score_gemma":0.00002397662,"domain_scores_codex":[0.9941961,0.00009136362,0.001227537,0.00176617,0.001454571,0.001264277],"domain_scores_gemma":[0.997089,0.0005965916,0.0006491987,0.001166992,0.0003169105,0.0001812826],"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":[0.00000328148,0.000006876449,0.0001154879,0.00008002303,0.00001203196,0.00009558878,0.0007440406,0.7835004,0.0001217668,0.006227858,0.000001965125,0.2090907],"study_design_scores_gemma":[0.0003384248,0.0001904972,0.00001304654,0.002625632,0.000010535,0.00003871673,0.00000136928,0.9895552,0.0003547858,0.005071061,0.001045173,0.0007555794],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00005377859,0.0002296286,0.991496,0.0002879552,0.001128469,0.0008245244,3.499963e-7,0.0002437589,0.005735582],"genre_scores_gemma":[0.2494271,0.00005357381,0.7479348,0.0009354082,0.0002466653,0.00001742314,0.000007848992,0.00005040571,0.001326776],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2493733,"threshold_uncertainty_score":0.9998816,"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."}}