{"id":"W4280563754","doi":"10.18196/jrc.v3i2.13082","title":"Consensus of Multi-agent Reinforcement Learning Systems: The Effect of Immediate Rewards","year":2022,"lang":"en","type":"article","venue":"Journal of Robotics and Control (JRC)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Reinforcement learning; Cumulative prospect theory; Computer science; Function (biology); Artificial intelligence; Mathematics; Statistics","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":[0.002996858,0.0001775789,0.0006122473,0.0001725518,0.0002401689,0.00007200014,0.0007224144,0.00004290389,0.000007042472],"category_scores_gemma":[0.0003543509,0.0001189495,0.0002048057,0.0002214967,0.0001030676,0.00008464453,0.0003162427,0.000580873,8.526339e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008144337,"about_ca_system_score_gemma":0.0001224339,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002806152,"about_ca_topic_score_gemma":3.594947e-7,"domain_scores_codex":[0.9969596,0.0006460265,0.001080892,0.0001431408,0.0009052966,0.0002650906],"domain_scores_gemma":[0.9965171,0.0008765372,0.001899388,0.0003318166,0.0002744227,0.0001007657],"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":[0.0001218444,0.0000183896,0.00333901,0.00009148377,0.0002297386,0.00002798547,0.0004666042,0.9925203,0.0010346,0.001329142,0.0001111512,0.0007097212],"study_design_scores_gemma":[0.003694912,0.003323835,0.0006993586,0.00008637977,0.0001566463,0.0001540275,0.0002849901,0.9900368,0.0002751517,0.000009186078,0.001157415,0.0001212722],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02034585,0.002235281,0.9747054,0.0008191925,0.001276133,0.0004393958,0.000001791722,0.00001380893,0.0001631232],"genre_scores_gemma":[0.9979337,0.0001246859,0.001499104,0.00005961738,0.00006375281,0.000006223611,6.0115e-7,0.0000121596,0.0003001297],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9775879,"threshold_uncertainty_score":0.4850618,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01050280994847894,"score_gpt":0.233200328614998,"score_spread":0.2226975186665191,"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."}}