{"id":"W150352456","doi":"10.5072/zenodo.49098","title":"Learning by Automatic Option Discovery from Conditionally Terminating Sequences","year":2006,"lang":"en","type":"article","venue":"OpenMETU (Middle East Technical University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Normalization property; Computer science; Reinforcement learning; Tree (set theory); Tree structure; Artificial intelligence; Machine learning; Theoretical computer science; Data structure; Programming language; 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":[],"consensus_categories":[],"category_scores_codex":[0.000216029,0.0001988696,0.0002265939,0.0002017017,0.0003914635,0.0004402136,0.001307436,0.0001317384,0.00007169474],"category_scores_gemma":[0.00008836498,0.0002171484,0.0001012369,0.0006699977,0.0001579873,0.002221892,0.0005875435,0.0003846305,0.000113918],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002491989,"about_ca_system_score_gemma":0.00008530886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002000606,"about_ca_topic_score_gemma":0.00001229614,"domain_scores_codex":[0.9982593,0.0001522799,0.0002793681,0.0004964572,0.0004858047,0.0003268048],"domain_scores_gemma":[0.9989974,0.0002187897,0.0002659212,0.000366236,0.00006852632,0.00008308083],"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":[0.00001972634,0.0002678488,0.005175579,0.00004886247,0.00008668967,0.0003780014,0.0002239771,0.5463316,0.03575622,0.4003079,0.001688007,0.009715641],"study_design_scores_gemma":[0.00159943,0.0004816063,0.01018708,0.0004555722,0.00008961108,0.00004658612,0.0006403773,0.9550464,0.001834888,0.004773656,0.02357578,0.001268998],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04535938,0.00001920168,0.9329847,0.0002343074,0.0001010863,0.0001875075,0.00001109967,0.0004592204,0.02064357],"genre_scores_gemma":[0.9351308,0.000005270019,0.04935737,0.00004957105,0.00004564617,0.000001900833,0.0001202912,0.00001258283,0.01527653],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8897715,"threshold_uncertainty_score":0.8855053,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01296326288476426,"score_gpt":0.195086123863933,"score_spread":0.1821228609791688,"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."}}