{"id":"W3165914412","doi":"","title":"Pretraining Reward-Free Representations for Data-Efficient Reinforcement Learning","year":2021,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"HEC Montréal; Université de Montréal","funders":"","keywords":"Reinforcement learning; Computer science; Reinforcement; Artificial intelligence; Cognitive psychology; Machine learning; Human–computer interaction; Psychology; Social psychology","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008302111,0.0003024425,0.0002840509,0.0003532983,0.0008138453,0.0010657,0.003043318,0.0001161765,0.0005129276],"category_scores_gemma":[0.007916275,0.0003422202,0.0001645824,0.0005912839,0.0001071393,0.0008320797,0.001710265,0.0007976589,0.000142205],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001740268,"about_ca_system_score_gemma":0.0004939393,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005232038,"about_ca_topic_score_gemma":0.00001018731,"domain_scores_codex":[0.995858,0.0002992954,0.0007976148,0.001275407,0.001245145,0.0005245395],"domain_scores_gemma":[0.9947122,0.001099628,0.0005250855,0.002130747,0.001351911,0.0001804707],"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":[0.00001893182,0.00005730783,0.001243633,0.00001230989,0.0001313988,0.00002176469,0.001854016,0.8096831,0.0006250926,0.1810927,0.001992023,0.003267748],"study_design_scores_gemma":[0.001038221,0.0001482398,0.0008185632,0.0001061119,0.00003046664,0.00003016956,0.001398453,0.9768035,0.0006078791,0.00153359,0.01713864,0.0003461904],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008749011,0.00002146614,0.9002134,0.007407912,0.001177641,0.0004214643,0.00001482015,0.0004282017,0.08944021],"genre_scores_gemma":[0.884539,0.00008089446,0.07542964,0.0003183084,0.0002937571,0.0002101965,0.001556604,0.00004798891,0.0375236],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8836641,"threshold_uncertainty_score":0.9999713,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1276518897166019,"score_gpt":0.378776401532506,"score_spread":0.2511245118159041,"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."}}