{"id":"W4415428256","doi":"10.3233/faia251090","title":"Skill-Enhanced Reinforcement Learning Acceleration from Heterogeneous Demonstrations","year":2025,"lang":"","type":"book-chapter","venue":"Frontiers in artificial intelligence and applications","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; Carleton University","funders":"","keywords":"Reinforcement learning; Leverage (statistics); Downstream (manufacturing); Temporal difference learning; Acceleration; Supervised learning; Online machine learning; Reinforcement","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"],"consensus_categories":[],"category_scores_codex":[0.0003853666,0.0007717366,0.0007764346,0.000764698,0.00122591,0.0009581471,0.001220861,0.0006489147,0.0002618817],"category_scores_gemma":[0.0001163243,0.0009502052,0.0002240364,0.0005776177,0.0005376593,0.0006053328,0.0005297823,0.001355938,0.0001900502],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003349854,"about_ca_system_score_gemma":0.0003470031,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001170184,"about_ca_topic_score_gemma":0.0000861513,"domain_scores_codex":[0.994891,0.0001014311,0.002109734,0.001586455,0.0006204594,0.0006908934],"domain_scores_gemma":[0.9971253,0.0003171953,0.0008455629,0.001118443,0.0003535498,0.000239976],"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":[0.00001544691,0.00003646249,0.00006009252,0.00003059101,0.00008136958,0.000002716685,0.0005670188,0.5749958,0.00009700574,0.1874231,0.00006389184,0.2366266],"study_design_scores_gemma":[0.0000718438,0.000158374,0.00001798375,0.0004880268,0.0001263162,0.000002198088,0.0005257343,0.8975163,0.005215156,0.08038431,0.01462974,0.0008640615],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00004147003,0.0008282218,0.9607646,0.0004032472,0.001039932,0.002060908,0.00001702705,0.0001450022,0.03469961],"genre_scores_gemma":[0.8380992,0.01227785,0.1001157,0.0005036823,0.0008442687,0.00118453,0.0007408345,0.0001016399,0.0461323],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8606489,"threshold_uncertainty_score":0.9992948,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03288550673780755,"score_gpt":0.2740642108823426,"score_spread":0.2411787041445351,"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."}}