{"id":"W1556824961","doi":"10.1007/3-540-45622-8_16","title":"Learning Options in Reinforcement Learning","year":2002,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":270,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Computer science; Psychology; Artificial intelligence","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":[0.0008140765,0.0006318201,0.0006800895,0.000288508,0.0002610897,0.001121903,0.0007976601,0.0008988484,0.007125658],"category_scores_gemma":[0.002913787,0.0003402363,0.000391677,0.0004951528,0.001527469,0.002565952,0.0008071463,0.002286638,0.0008303144],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006548396,"about_ca_system_score_gemma":0.0003064063,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005394966,"about_ca_topic_score_gemma":0.000620177,"domain_scores_codex":[0.9996715,0.0001679115,0.00001474787,0.00004713654,0.00007814249,0.00002058658],"domain_scores_gemma":[0.9990978,0.000738562,0.00002939278,0.00005775956,0.00004685892,0.00002963823],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004223638,0.00004484657,0.0002077991,0.0001324464,0.0000262381,0.0000570968,0.0001197947,0.07452527,0.0004648939,0.7852796,0.004638289,0.1344615],"study_design_scores_gemma":[0.00001462453,0.00002195527,0.00006504189,0.00003106277,0.000007649739,0.00002769291,0.00001740859,0.1537765,0.0003155732,0.8397244,0.005989775,0.000008328362],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01452439,0.006235654,0.9178274,0.001506719,0.0003095269,0.00003816838,0.00006440291,0.0002838838,0.05920988],"genre_scores_gemma":[0.6823305,0.006068602,0.251051,0.0004175187,0.0004628431,0.0002897172,0.0001939879,0.0001673007,0.05901855],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007125658,"threshold_uncertainty_score":0.02383769,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02108976112327637,"score_gpt":0.2445734416842048,"score_spread":0.2234836805609284,"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."}}