{"id":"W2123975568","doi":"10.1109/ictai.2001.974465","title":"Developing collaborative Golog agents by reinforcement learning","year":2001,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Reinforcement learning; Scalability; Human–computer interaction; Plan (archaeology); Knowledge management; Artificial intelligence; Database","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":[0.000297229,0.0001855594,0.0001668174,0.00009703924,0.0002851222,0.0002497525,0.0007742486,0.00007097788,0.000152683],"category_scores_gemma":[0.0001239894,0.0001725668,0.00003574762,0.0007875606,0.0000382269,0.0005903323,0.0004043124,0.0002153916,0.0004239907],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001837771,"about_ca_system_score_gemma":0.000140439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001942615,"about_ca_topic_score_gemma":0.000001815814,"domain_scores_codex":[0.9983412,0.0000843259,0.0003361373,0.0003539906,0.0004279539,0.0004563977],"domain_scores_gemma":[0.9991381,0.00008749896,0.000162835,0.000345713,0.000165589,0.0001003245],"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":[0.000005400198,0.000009293003,0.004289231,0.000006713207,0.00004237409,0.00002146309,0.0008152034,0.906433,0.0001313929,0.06452534,0.02039373,0.003326849],"study_design_scores_gemma":[0.0004180356,0.0001641742,0.0004144358,0.00002131043,0.000003833117,0.00001059936,0.0001889689,0.6184616,0.001092705,0.0001373938,0.3787594,0.0003275246],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001448433,0.00003332804,0.9124458,0.001106466,0.0002365341,0.0001857248,7.314384e-8,0.0003421075,0.08420149],"genre_scores_gemma":[0.7710415,0.0003091967,0.1210452,0.002623039,0.00005607424,0.00003417119,0.00002555904,0.00002457946,0.1048406],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7914006,"threshold_uncertainty_score":0.7037069,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02568505897910089,"score_gpt":0.2794036388692177,"score_spread":0.2537185798901168,"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."}}