{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001032102,0.0008514776,0.0006539732,0.000388988,0.000532942,0.0008172523,0.001454675,0.001041528,0.002154441],"category_scores_gemma":[0.003766707,0.0004967421,0.0003952862,0.0002551307,0.001178707,0.00127879,0.001800227,0.0008548553,0.0005758752],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005820554,"about_ca_system_score_gemma":0.00106254,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002732444,"about_ca_topic_score_gemma":0.002935669,"domain_scores_codex":[0.9995414,0.0001515072,0.00002679158,0.00009924922,0.0001054133,0.00007555677],"domain_scores_gemma":[0.998831,0.0005076771,0.0001979744,0.000173066,0.0001605612,0.0001297132],"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":[0.0001210759,0.0002320164,0.002261013,0.0001234352,0.00007811197,0.0002774414,0.0004112523,0.8824722,0.008153123,0.02201266,0.001477297,0.08238041],"study_design_scores_gemma":[0.00003240218,0.00006886074,0.0001137154,0.00001092704,0.00001047479,0.00003496188,0.00003596572,0.9859568,0.002140342,0.009319239,0.002267357,0.000009068909],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05244835,0.0001450481,0.9428107,0.00018397,0.0000289558,0.0001554208,0.00002285885,0.001002262,0.003202503],"genre_scores_gemma":[0.536665,0.0002177873,0.4588378,0.0001110854,0.00002807506,0.0003640544,0.00009151484,0.0001220959,0.003562494],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002732444,"threshold_uncertainty_score":0.007207334,"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."}}