{"id":"W4403851978","doi":"10.48550/arxiv.2410.01643","title":"Stable Offline Value Function Learning with Bisimulation-based Representations","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Instituto de Ciencias del Mar y Limnología, Universidad Nacional Autónoma de México; Sandia National Laboratories; University of Wisconsin-Madison; Institute for Catastrophic Loss Reduction; National Science Foundation","keywords":"Bisimulation; Value (mathematics); Function (biology); Computer science; Mathematics; Theoretical computer science; Artificial intelligence; Machine learning","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003842485,0.001468706,0.001653796,0.0007923107,0.0006169796,0.001825186,0.002193412,0.001867719,0.002303423],"category_scores_gemma":[0.02092434,0.0008862021,0.0008296347,0.0005655222,0.002356583,0.004290079,0.003168636,0.003724811,0.0006884509],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002370314,"about_ca_system_score_gemma":0.002519683,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003516999,"about_ca_topic_score_gemma":0.002783382,"domain_scores_codex":[0.997973,0.0009185838,0.0001331023,0.0004187585,0.0003500861,0.0002063846],"domain_scores_gemma":[0.9905797,0.006146359,0.0009363979,0.001103377,0.0009212138,0.0003129655],"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":[0.0002735006,0.0001929665,0.001371047,0.00008734538,0.00006888021,0.00005924926,0.0001878514,0.8550515,0.00233293,0.05849496,0.0009206113,0.08095912],"study_design_scores_gemma":[0.000009458719,0.00003135604,0.00002471869,0.000006685389,0.000002992826,0.0000051101,0.000005127894,0.984848,0.0006096525,0.01433719,0.000115037,0.000004719557],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03142791,0.000130123,0.9661451,0.0002541121,0.00002445683,0.00007531401,0.00003923194,0.0006502282,0.001253467],"genre_scores_gemma":[0.7910077,0.0001498806,0.2053302,0.0002597126,0.00003535803,0.0003871298,0.0002055111,0.0002964306,0.002328083],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003842485,"threshold_uncertainty_score":0.02032125,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05318057816770258,"score_gpt":0.1993830184167592,"score_spread":0.1462024402490566,"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."}}