{"id":"W3208994216","doi":"10.48550/arxiv.2110.14096","title":"Towards Robust Bisimulation Metric Learning","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Embedding; Computer science; Robustness (evolution); Artificial intelligence; Representation (politics); Theoretical computer science","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":[0.004636302,0.001915523,0.001852279,0.001215285,0.0004566309,0.001868523,0.001963668,0.001830064,0.001817627],"category_scores_gemma":[0.02256947,0.0009954742,0.0008103641,0.0007862161,0.002211031,0.003754201,0.005212707,0.004476962,0.0005927837],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002209078,"about_ca_system_score_gemma":0.001895023,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002133969,"about_ca_topic_score_gemma":0.00170886,"domain_scores_codex":[0.9970155,0.001512532,0.0001544564,0.0005335918,0.0006085174,0.0001753177],"domain_scores_gemma":[0.9915804,0.005163124,0.0009640545,0.0009566805,0.000914158,0.0004214025],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001552447,0.00008943938,0.0007729051,0.0001477209,0.00007874067,0.00003916779,0.0001445912,0.806215,0.002397892,0.1221424,0.001487483,0.06632949],"study_design_scores_gemma":[0.000005883095,0.00002962968,0.00003708181,0.000009475499,0.000002373909,0.000005868772,0.000005496884,0.9680499,0.0004180657,0.03114974,0.0002810583,0.00000535806],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01035317,0.0001795037,0.9881247,0.0002264615,0.00001968546,0.00002860699,0.00003944607,0.0002897578,0.0007386788],"genre_scores_gemma":[0.6103864,0.0004475359,0.3843434,0.0003404844,0.00009989482,0.0003758442,0.0004173728,0.0005223351,0.003066662],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004636302,"threshold_uncertainty_score":0.02451938,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09633591901691252,"score_gpt":0.1997533717924085,"score_spread":0.103417452775496,"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."}}