{"id":"W2095564494","doi":"10.1142/s0219525911002998","title":"AN EMPIRICAL STUDY OF POTENTIAL-BASED REWARD SHAPING AND ADVICE IN COMPLEX, MULTI-AGENT SYSTEMS","year":2011,"lang":"en","type":"article","venue":"Advances in Complex Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":79,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Computer science; Context (archaeology); Reward system; Nash equilibrium; Domain (mathematical analysis); Artificial intelligence; Machine learning; Psychology; Mathematical optimization; Mathematics","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":[0.001015073,0.0003044305,0.0007055748,0.000437252,0.0001076955,0.0001343322,0.001216765,0.00008585678,0.000005223244],"category_scores_gemma":[0.00004786845,0.000296097,0.00004246966,0.0006863797,0.0001088616,0.0008622232,0.0002675608,0.0002509536,0.000006893532],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001366853,"about_ca_system_score_gemma":0.00004829575,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001750264,"about_ca_topic_score_gemma":0.0003332242,"domain_scores_codex":[0.9961606,0.0007705003,0.001233161,0.0007308532,0.0006142443,0.0004906777],"domain_scores_gemma":[0.9980476,0.0001671948,0.0005286206,0.0009674509,0.0001485058,0.0001405562],"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":[0.00002434846,0.0004801769,0.19728,0.0003002734,0.00001439981,0.00005821868,0.003976537,0.7968854,0.0002168599,0.0005309256,0.00001801386,0.0002148772],"study_design_scores_gemma":[0.001746901,0.0006825228,0.1014351,0.0002015639,0.000007591191,0.00001606726,0.002993246,0.8920888,0.000007462443,0.00001176295,0.0005215248,0.0002874701],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1564976,0.001219831,0.839312,0.00001651527,0.0007874885,0.001483828,0.000003316151,0.0001905181,0.0004889802],"genre_scores_gemma":[0.9781694,0.00002267529,0.02159936,0.00004245591,0.00003789339,0.00007763507,0.000008129164,0.00002340907,0.0000190565],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8216718,"threshold_uncertainty_score":0.9999491,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1324506532271785,"score_gpt":0.3578127690604147,"score_spread":0.2253621158332362,"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."}}