{"id":"W2567143531","doi":"10.6084/m9.figshare.3085861.v1","title":"Reinforcement Learning in a Nutshell","year":2016,"lang":"en","type":"article","venue":"Figshare","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Reinforcement; Artificial intelligence; Reinforcement learning; Computer science; Psychology; Social psychology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00008375951,0.0001121034,0.0001018852,0.0001174952,0.00005028998,0.00008382335,0.0007048458,0.00005430148,0.0298175],"category_scores_gemma":[0.000821701,0.00008214253,0.00004045158,0.0002607185,0.000003853275,0.000473617,0.0004025027,0.0001407838,0.007303486],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009655004,"about_ca_system_score_gemma":0.00006047869,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002331759,"about_ca_topic_score_gemma":0.000001198369,"domain_scores_codex":[0.9989068,0.00003822795,0.00021166,0.0002515326,0.0002642726,0.0003274883],"domain_scores_gemma":[0.9992517,0.0001626387,0.00009456712,0.0003759603,0.00004926091,0.00006583539],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000006494726,0.00001952894,0.001331094,0.0000876378,0.00001431023,0.00008466846,0.0006201749,0.8150157,0.0005103521,0.003462509,0.1363515,0.04249603],"study_design_scores_gemma":[0.001055071,0.0002000452,0.003511415,0.00261374,0.00000131646,0.00001030048,0.00001352555,0.3621294,0.002071356,0.0001310964,0.6277889,0.0004738619],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002836689,0.00016197,0.8554495,0.00237492,0.0004026041,0.0009331745,0.0007074556,0.001600201,0.1380865],"genre_scores_gemma":[0.9768835,0.000008789905,0.002747461,0.0004449574,0.0000850567,0.0001342827,0.001331986,0.00002326847,0.01834075],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9765998,"threshold_uncertainty_score":0.9934694,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02945892669748738,"score_gpt":0.2467330003325303,"score_spread":0.217274073635043,"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."}}