{"id":"W4214671235","doi":"10.36227/techrxiv.19172369","title":"Deep Reinforcement Learning in Human Activity Recognition: A Survey","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Context-Aware Activity Recognition Systems","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Reinforcement learning; Activity recognition; Field (mathematics); Computer science; Deep learning; Artificial intelligence; Key (lock); Human–computer interaction; Data science; Machine learning; Computer security","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003120922,0.0004201374,0.0006559402,0.0006037878,0.0003216664,0.0005038887,0.001434799,0.0002564053,0.001908504],"category_scores_gemma":[0.0002514198,0.0004953076,0.0002101776,0.000674003,0.00003442051,0.0006051683,0.004968844,0.002144752,0.0001457091],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007193923,"about_ca_system_score_gemma":0.0003207083,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01100004,"about_ca_topic_score_gemma":0.008545068,"domain_scores_codex":[0.9947617,0.002009772,0.0006678079,0.001275446,0.0007986827,0.0004865851],"domain_scores_gemma":[0.9973551,0.0006064774,0.0005680234,0.00111463,0.0002212163,0.0001345298],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001387088,0.001151764,0.05703365,0.0006766787,0.000434997,0.0003318356,0.006067186,0.08271603,0.0006757019,0.000764913,0.001782796,0.8482257],"study_design_scores_gemma":[0.0034861,0.0007852999,0.224779,0.0007155003,0.00004292512,0.00009757444,0.0005712255,0.7488993,0.00202537,0.005946785,0.008108188,0.004542783],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1190073,0.00005293585,0.8416297,0.0003302277,0.001473219,0.001276539,0.000009073317,0.0008008629,0.03542009],"genre_scores_gemma":[0.9953119,0.00001708021,0.0007022873,0.0001470866,0.00008417187,0.0005941187,0.0002704308,0.00002988619,0.002843017],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8763046,"threshold_uncertainty_score":0.9997498,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1012036164233027,"score_gpt":0.313864409012136,"score_spread":0.2126607925888332,"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."}}