{"id":"W7124320494","doi":"10.65109/vaba4866","title":"PADDLE: Logic Program Guided Policy Reuse in Deep Reinforcement Learning","year":2024,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reuse; Reinforcement learning; Metric (unit); Transferability; Task (project management); Similarity (geometry); Measure (data warehouse)","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","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002022068,0.0008849897,0.0007091046,0.001708737,0.0003812775,0.003486871,0.00365892,0.0004574273,0.001012091],"category_scores_gemma":[0.001994317,0.0008394296,0.0003578976,0.005445724,0.0002761767,0.001633014,0.003677612,0.002004273,0.002422711],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001257051,"about_ca_system_score_gemma":0.001245211,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005700891,"about_ca_topic_score_gemma":0.00002400249,"domain_scores_codex":[0.9920112,0.0004669043,0.002113685,0.001712554,0.001506981,0.002188622],"domain_scores_gemma":[0.9961861,0.0003229762,0.0003332997,0.0024424,0.0002476485,0.0004676043],"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":[0.00000986149,0.00008097304,0.000485125,0.0003293095,0.00008659968,0.000304301,0.003873895,0.7942291,0.00005446951,0.1137333,0.001592233,0.08522081],"study_design_scores_gemma":[0.0006136302,0.001323131,0.0002816517,0.0006821594,0.00003352809,0.00004194471,0.0001748158,0.9128045,0.000142906,0.001111207,0.0819179,0.0008726031],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004892696,0.001188567,0.9012169,0.008925286,0.001722647,0.001826884,1.859877e-7,0.001812365,0.08281787],"genre_scores_gemma":[0.8380229,0.001260457,0.06416119,0.001297998,0.0006494627,0.0002047929,0.00002390433,0.0001098489,0.09426937],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8375337,"threshold_uncertainty_score":0.9999011,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04022714982400774,"score_gpt":0.3343178041523078,"score_spread":0.2940906543283001,"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."}}