{"id":"W2109875442","doi":"10.1142/s0218213002000873","title":"DEVELOPING COLLABORATIVE GOLOG AGENTS BY REINFORCEMENT LEARNING","year":2002,"lang":"en","type":"article","venue":"International Journal of Artificial Intelligence Tools","topic":"Multi-Agent Systems and Negotiation","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Reinforcement learning; Scalability; Human–computer interaction; 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":[0.0005421032,0.0001354315,0.0001868369,0.0002128382,0.0001134468,0.0004605471,0.001042195,0.00006154484,0.0002611045],"category_scores_gemma":[0.0004026986,0.0001227458,0.00009367611,0.0002822862,0.00003510192,0.001276179,0.0001188732,0.0002205376,0.0002169892],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002438299,"about_ca_system_score_gemma":0.00007209203,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001456989,"about_ca_topic_score_gemma":0.000004188847,"domain_scores_codex":[0.9977853,0.0001116802,0.0009261346,0.0001870628,0.0007928064,0.0001969706],"domain_scores_gemma":[0.9978501,0.0001639205,0.0007741324,0.0001208169,0.001005445,0.00008560647],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007957555,0.0002842322,0.0008395585,0.00001361226,0.0004464581,0.0002061059,0.009674687,0.06650843,0.009019029,0.1696709,0.01714037,0.7261171],"study_design_scores_gemma":[0.0003310103,0.0006683902,0.0004753944,0.000376572,0.00002210243,0.0002036056,0.001623514,0.7263343,0.146867,0.00724208,0.1151413,0.0007147019],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01576498,0.0001731009,0.9776722,0.002868129,0.002150243,0.0001232953,0.000002311804,0.00002756039,0.001218197],"genre_scores_gemma":[0.9887494,0.0002681111,0.009720129,0.0003572614,0.0003094771,0.000004569102,0.000003993997,0.00000745773,0.000579577],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9729844,"threshold_uncertainty_score":0.5005427,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1117068500660333,"score_gpt":0.3394125118227033,"score_spread":0.22770566175667,"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."}}