{"id":"W2735649811","doi":"10.1007/s10994-017-5657-1","title":"Generalized exploration in policy search","year":2017,"lang":"en","type":"article","venue":"Machine Learning","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"Seventh Framework Programme; Technische Universität Darmstadt","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Entropy (arrow of time); Policy learning; Machine learning; Mathematical optimization; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0006428226,0.0001163312,0.0001400041,0.0002491295,0.0005559248,0.0006979775,0.001129786,0.00005046502,0.00002222208],"category_scores_gemma":[0.0005954194,0.0001151773,0.00003848538,0.0001780208,0.00003782937,0.001126776,0.0005845507,0.0003973382,0.0001152593],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007797277,"about_ca_system_score_gemma":0.00006998652,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001332497,"about_ca_topic_score_gemma":0.00005964848,"domain_scores_codex":[0.9987234,0.0001734769,0.0002021854,0.0002707607,0.0003009841,0.0003292344],"domain_scores_gemma":[0.9990062,0.00004563515,0.0001415299,0.0007043636,0.00003925746,0.00006300445],"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":[0.000003808433,0.000007321504,0.04780951,0.000006726807,0.000003939082,0.00001467867,0.001040809,0.906871,0.0003919131,0.02692618,0.00002131341,0.01690277],"study_design_scores_gemma":[0.0005045746,0.00005081924,0.01737688,0.00001656786,8.702331e-7,0.000003161119,0.00001364359,0.9765167,0.0002714444,0.0003441896,0.004770864,0.0001302397],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03380511,0.00003210797,0.9499956,0.005321826,0.0001569491,0.0001212898,1.273012e-7,0.0001653145,0.0104017],"genre_scores_gemma":[0.9777511,0.00003854059,0.01760766,0.0001528087,0.0001336055,0.000008388068,0.000006124803,0.00001409848,0.004287634],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.943946,"threshold_uncertainty_score":0.6730613,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05004398310810728,"score_gpt":0.3319969426844179,"score_spread":0.2819529595763107,"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."}}