{"id":"W2538613533","doi":"10.1109/gem.2014.7048106","title":"Enabling motivated believable agents with reinforcement learning","year":2014,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Reinforcement learning; Computer science; Action (physics); Narrative; Reinforcement; Human–computer interaction; Video game; Variety (cybernetics); Artificial intelligence; Multimedia; Psychology; Social psychology","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":[0.001201393,0.0007642982,0.0003592485,0.0002419035,0.0003046903,0.00077669,0.001042786,0.0007612689,0.001839252],"category_scores_gemma":[0.005142406,0.0003813655,0.0003988234,0.0001162265,0.001080478,0.001067902,0.001720882,0.001398487,0.0003274044],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006084258,"about_ca_system_score_gemma":0.0007570382,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001749767,"about_ca_topic_score_gemma":0.001921284,"domain_scores_codex":[0.9993898,0.0002767288,0.00003021949,0.00007941081,0.0001523753,0.00007148025],"domain_scores_gemma":[0.9981668,0.001158303,0.0002234202,0.0001543301,0.0001672573,0.0001298229],"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":[0.0001711747,0.0003873941,0.002270672,0.0001765987,0.00006766283,0.0002526222,0.0004512743,0.8509889,0.01595429,0.05669668,0.001209047,0.07137369],"study_design_scores_gemma":[0.00003787663,0.00007092474,0.0001037212,0.00001220965,0.000007975884,0.00002469312,0.00002177652,0.9755057,0.002691473,0.0202468,0.001267686,0.000009291287],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09361356,0.0001761236,0.8975568,0.00044895,0.00004549758,0.0001839543,0.00002720466,0.001133151,0.006814794],"genre_scores_gemma":[0.8574349,0.0001302342,0.1395827,0.0001519191,0.00001536657,0.0002529604,0.00004149274,0.00007160774,0.002318863],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.001839252,"threshold_uncertainty_score":0.006353617,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01487778693265295,"score_gpt":0.2251461700584045,"score_spread":0.2102683831257515,"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."}}