{"id":"W3214251933","doi":"","title":"A Minimalist Approach to Offline Reinforcement Learning","year":2021,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Computer science; Leverage (statistics); Hyperparameter; Offline learning; Artificial intelligence; Machine learning; Online algorithm; Algorithm; Online 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001404786,0.001146707,0.001496363,0.0005905306,0.0005377062,0.001418881,0.002936364,0.001136629,0.007360719],"category_scores_gemma":[0.006882076,0.0008911081,0.0007864666,0.0004751051,0.001646661,0.001891415,0.002402997,0.003018552,0.001355967],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001459252,"about_ca_system_score_gemma":0.002156309,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00430335,"about_ca_topic_score_gemma":0.007372234,"domain_scores_codex":[0.9986064,0.0003776508,0.00007027292,0.0004285323,0.000376704,0.0001405341],"domain_scores_gemma":[0.997113,0.001770627,0.0001721263,0.0004703893,0.0003457182,0.0001281692],"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":[0.0001464883,0.0001624236,0.000760121,0.0001740439,0.0001041651,0.00009176328,0.0001312595,0.7811735,0.002612407,0.08107091,0.004400086,0.1291729],"study_design_scores_gemma":[0.00001038333,0.00002763694,0.00005593992,0.000007394411,0.000006590865,0.00001552304,0.000004383802,0.9727622,0.0005006624,0.02560963,0.0009932577,0.000006414587],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002739172,0.00007662189,0.9933623,0.0001801644,0.00002852089,0.00003981579,0.00004972818,0.0008058755,0.00271774],"genre_scores_gemma":[0.5228709,0.0002378301,0.4619877,0.0004967355,0.0001845558,0.0004951595,0.0003833766,0.0006168772,0.01272682],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007360719,"threshold_uncertainty_score":0.02462411,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02581352480745651,"score_gpt":0.2637669248935865,"score_spread":0.23795340008613,"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."}}