{"id":"W7124326325","doi":"10.65109/sjgw9760","title":"Empowering Generalization for Deep Reinforcement Learning via Symbolic Planning","year":2025,"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":"Reinforcement learning; Generalization; Pearl; Planner; Limiting; Automated planning and scheduling; Plan (archaeology); Deep learning","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":[0.001184134,0.0009145749,0.0007665437,0.0003496797,0.0003262575,0.0005699902,0.001258947,0.000789472,0.002372826],"category_scores_gemma":[0.004902762,0.0004233705,0.0005212019,0.0003353086,0.001349362,0.001592508,0.001563007,0.002231921,0.0003302623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009684565,"about_ca_system_score_gemma":0.001379746,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005029621,"about_ca_topic_score_gemma":0.007883764,"domain_scores_codex":[0.9995921,0.0001377935,0.00002251162,0.0001144939,0.00007657372,0.00005642709],"domain_scores_gemma":[0.9984533,0.0009659455,0.0001213857,0.0002737122,0.0001099158,0.00007585652],"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":[0.0000848791,0.00007594304,0.001003996,0.00009265579,0.0000361297,0.00006600009,0.00008392423,0.8943962,0.002119633,0.01211525,0.001391593,0.08853374],"study_design_scores_gemma":[0.000009894693,0.00002186673,0.0000537571,0.000005874602,0.00000337359,0.000006105602,0.000004424991,0.9911115,0.0004296807,0.008084093,0.0002666168,0.000002835461],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05417644,0.0004553464,0.9391499,0.0005207033,0.00004319304,0.00006897996,0.000113726,0.002201695,0.003269971],"genre_scores_gemma":[0.8668857,0.0002140988,0.1306775,0.0001887018,0.00002143479,0.0001507514,0.0001931668,0.0001074085,0.001561181],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005029621,"threshold_uncertainty_score":0.01000071,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01938705309028489,"score_gpt":0.3083807653414555,"score_spread":0.2889937122511707,"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."}}