{"id":"W3185313117","doi":"","title":"Exploration-Driven Representation Learning in Reinforcement Learning","year":2021,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Representation (politics); Machine learning","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":[0.0005312223,0.0002896194,0.0002828514,0.0004522982,0.00030638,0.0006853321,0.0008472953,0.0001117583,0.0006811006],"category_scores_gemma":[0.001559316,0.0003244915,0.00009533347,0.0006283116,0.00004042054,0.001325276,0.0005101084,0.001656628,0.0003468063],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002538527,"about_ca_system_score_gemma":0.0001985947,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001151198,"about_ca_topic_score_gemma":0.00004189649,"domain_scores_codex":[0.9965946,0.0005476467,0.0006665944,0.0007410788,0.001028133,0.0004219278],"domain_scores_gemma":[0.9983242,0.0002912615,0.0004218429,0.000361478,0.0004928169,0.000108446],"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":[0.00002085785,0.00002929374,0.02576623,0.000007653563,0.0000340037,0.00009457509,0.001315749,0.8882368,0.001961356,0.07560354,0.00002488528,0.00690512],"study_design_scores_gemma":[0.0007856997,0.0002286176,0.002072945,0.0001461195,0.000004890547,0.00001899382,0.000533653,0.9865861,0.0009962178,0.0007037591,0.007598469,0.0003245672],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007037508,0.00003059396,0.913184,0.004884087,0.0006748372,0.0001764807,3.554308e-7,0.0004046244,0.07360747],"genre_scores_gemma":[0.9735579,0.0002649285,0.006391867,0.0002856065,0.0001188115,0.00004026738,0.0002359107,0.00002847389,0.01907618],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9665204,"threshold_uncertainty_score":0.9999207,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06580708750621926,"score_gpt":0.328197841659694,"score_spread":0.2623907541534747,"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."}}