{"id":"W4378438662","doi":"10.1007/978-3-031-33377-4_30","title":"Transfer Reinforcement Learning Based Negotiating Agent Framework","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Multi-Agent Systems and Negotiation","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Computer science; Reinforcement learning; Negotiation; Transfer of learning; Artificial intelligence; Human–computer interaction","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":[0.001392313,0.000568223,0.0005401437,0.0008895351,0.0004721668,0.0007931889,0.002171439,0.0004293518,0.00004035937],"category_scores_gemma":[0.0001849965,0.0005350671,0.000194235,0.000789489,0.0001869659,0.0006376012,0.0005481762,0.001224784,0.0001770193],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000374426,"about_ca_system_score_gemma":0.0004063495,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006132382,"about_ca_topic_score_gemma":0.00001976875,"domain_scores_codex":[0.9952837,0.0000751982,0.0007933693,0.001517666,0.001534794,0.0007953359],"domain_scores_gemma":[0.9973716,0.0008316343,0.0002637361,0.001126699,0.0002026428,0.0002037624],"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":[0.00000255914,0.000009471823,0.00004594078,0.00006051879,0.00001012523,0.0000433546,0.000828961,0.8908569,0.00008071506,0.02579687,0.00001088743,0.08225367],"study_design_scores_gemma":[0.0002377861,0.0001398149,0.0001037516,0.0008890227,0.00000795897,0.000006624839,4.34309e-7,0.9883956,0.0005104836,0.007647859,0.001465442,0.0005952022],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00005785167,0.0001368576,0.993429,0.0005206402,0.003894793,0.00057772,0.000001518417,0.0004364732,0.0009451504],"genre_scores_gemma":[0.7267002,0.0000856128,0.2663817,0.002560244,0.001360258,0.00005756779,0.00003030201,0.0001414199,0.002682655],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7270473,"threshold_uncertainty_score":0.9997101,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0304997900759824,"score_gpt":0.2572152722457057,"score_spread":0.2267154821697233,"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."}}