{"id":"W7061340269","doi":"","title":"Residual Learning and Context Encoding for Adaptive Offline-to-Online Reinforcement Learning","year":2024,"lang":"en","type":"article","venue":"Aaltodoc (Aalto University)","topic":"Magnetic confinement fusion research","field":"Physics and Astronomy","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Finnish Center for Artificial Intelligence; Business Finland; China Scholarship Council","keywords":"Reinforcement learning; Encoding (memory); Context (archaeology); Residual; Stability (learning theory); Reinforcement; Adaptive learning; Feature (linguistics)","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":[0.0009920142,0.0007643051,0.0008914563,0.0003064841,0.0002782736,0.0008831818,0.001443346,0.0009158956,0.007189586],"category_scores_gemma":[0.004189583,0.0004234413,0.0003830777,0.0003081077,0.000803025,0.001175243,0.001392826,0.001882053,0.0009911503],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007223357,"about_ca_system_score_gemma":0.0009938513,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007036513,"about_ca_topic_score_gemma":0.007595353,"domain_scores_codex":[0.9995856,0.0001254914,0.0000247144,0.0001049365,0.00006861537,0.00009072496],"domain_scores_gemma":[0.9986419,0.0009068648,0.00008081387,0.0001510983,0.0001348513,0.00008445839],"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":[0.0004606934,0.0002435358,0.0007123773,0.0001197874,0.00005838544,0.00008464851,0.00008725395,0.7204651,0.00341195,0.02210027,0.003958178,0.2482978],"study_design_scores_gemma":[0.00002112434,0.00005073917,0.00007757368,0.000007245997,0.000005080761,0.000008272577,0.000003886994,0.9933739,0.0004456168,0.005670476,0.0003313018,0.00000479884],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03668614,0.000861007,0.9541798,0.000345283,0.0001971689,0.00008231239,0.0001203133,0.001306692,0.006221318],"genre_scores_gemma":[0.8767566,0.0003211771,0.113521,0.0001728148,0.00009592038,0.0002132617,0.000209229,0.0002007245,0.008509246],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007189586,"threshold_uncertainty_score":0.02405149,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.020834519166541,"score_gpt":0.2640575432763022,"score_spread":0.2432230241097612,"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."}}