{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00154369,0.001025236,0.001133584,0.0004159604,0.0003558575,0.001788299,0.002035311,0.001503336,0.01595013],"category_scores_gemma":[0.005352992,0.0007976773,0.0007566359,0.0003520531,0.001193532,0.003331046,0.002707148,0.00415306,0.009433576],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005356197,"about_ca_system_score_gemma":0.001036647,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009833111,"about_ca_topic_score_gemma":0.001270877,"domain_scores_codex":[0.9993594,0.0001610879,0.00005883817,0.0001484862,0.0002335677,0.00003856505],"domain_scores_gemma":[0.9986219,0.0004903358,0.00007034132,0.0004126894,0.0003009205,0.0001037388],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002755828,0.0001888743,0.0006985704,0.0004790547,0.000249482,0.0001807222,0.0002031857,0.166662,0.007921016,0.2922976,0.02923111,0.5016127],"study_design_scores_gemma":[0.00008961884,0.0001703992,0.0002104927,0.000263256,0.00006836632,0.0002240498,0.00003811151,0.4670261,0.005387879,0.4587481,0.06770851,0.00006517093],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001279791,0.0005276956,0.987225,0.0009801126,0.0002334083,0.00007279075,0.00007509393,0.002603756,0.007002315],"genre_scores_gemma":[0.1150165,0.001526112,0.8527375,0.001298463,0.0003503003,0.0004952762,0.0003834339,0.001293277,0.02689921],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01595013,"threshold_uncertainty_score":0.05335855,"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."}}