{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001760195,0.0009265207,0.0008975321,0.0004346595,0.0003107319,0.0007539823,0.001851206,0.00103584,0.002642925],"category_scores_gemma":[0.005210537,0.0004267996,0.0004949296,0.0003220344,0.001138392,0.001700292,0.001641645,0.001850209,0.0003887292],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001209484,"about_ca_system_score_gemma":0.001790216,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003919579,"about_ca_topic_score_gemma":0.004027668,"domain_scores_codex":[0.9991193,0.0002828726,0.00004786083,0.0002250944,0.0001958067,0.0001290534],"domain_scores_gemma":[0.9985183,0.0008156074,0.0001795102,0.0001936014,0.0001587796,0.0001342324],"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":[0.0002681137,0.0003032979,0.002170202,0.0001830486,0.00008255785,0.0001175061,0.0001568232,0.7348244,0.005565677,0.01562216,0.002336965,0.2383693],"study_design_scores_gemma":[0.00001966753,0.00005694995,0.00006901112,0.000007102513,0.000006867639,0.00001025494,0.000005156423,0.9921903,0.001189912,0.006092064,0.0003475141,0.000005149606],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0259152,0.0002397686,0.9700527,0.0002183532,0.00003511435,0.0001013988,0.00005106954,0.001924185,0.001462221],"genre_scores_gemma":[0.8298859,0.0001628365,0.1662741,0.0003472406,0.00003005174,0.0002673106,0.0001548201,0.0001905379,0.002687132],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003919579,"threshold_uncertainty_score":0.009308934,"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."}}