{"id":"W4231805100","doi":"10.22215/etd/2012-09679","title":"Multi-agent reinforcement learning in games","year":2012,"lang":"en","type":"dissertation","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University; Canadian Heritage; Library and Archives Canada","funders":"","keywords":"Reinforcement learning; Humanities; Computer science; Artificial intelligence; Art","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004550245,0.0003645299,0.0003454441,0.00042896,0.0001008351,0.000197512,0.001035682,0.000278348,0.0003110707],"category_scores_gemma":[0.0001152158,0.0003518837,0.0001188933,0.0003684224,0.00001261805,0.0005104276,0.0001892204,0.0007976286,0.0006838508],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002148408,"about_ca_system_score_gemma":0.0001389839,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001316996,"about_ca_topic_score_gemma":0.0001048957,"domain_scores_codex":[0.9975899,0.0000824648,0.000629868,0.000466868,0.0006052317,0.000625681],"domain_scores_gemma":[0.9987451,0.00007028436,0.0003694191,0.0005971395,0.0000898631,0.0001281416],"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":[0.000006913512,0.00003809359,0.002327095,0.0001243294,0.00003298678,0.00001027193,0.003758338,0.9799502,0.0002996,0.003882921,0.0003976264,0.0091716],"study_design_scores_gemma":[0.0006562017,0.0001088279,0.03039918,0.0002426033,0.00001869873,0.000002741225,0.0005928124,0.9439887,0.0008842211,0.00001283387,0.02233691,0.0007562464],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001852815,0.0003142065,0.9312614,0.00005225213,0.001910602,0.0004561072,6.908802e-8,0.0003879264,0.06376465],"genre_scores_gemma":[0.5490905,0.0001596408,0.04206206,0.0001378365,0.0001030524,0.00007840536,0.000277079,0.00005159074,0.4080398],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8891993,"threshold_uncertainty_score":0.9998933,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02646687385412405,"score_gpt":0.2866958448495736,"score_spread":0.2602289709954496,"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."}}