{"id":"W3037476194","doi":"10.1609/icaps.v30i1.6750","title":"Symbolic Plans as High-Level Instructions for Reinforcement Learning","year":2020,"lang":"en","type":"article","venue":"Proceedings of the International Conference on Automated Planning and Scheduling","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":63,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Agencia Nacional de Investigación y Desarrollo","keywords":"Reinforcement learning; Computer science; Maximization; Task (project management); State (computer science); Action (physics); Artificial intelligence; Machine learning; Mathematical optimization; Programming language; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0009220642,0.0009569907,0.0005375133,0.0006097186,0.0004079099,0.001480293,0.001455946,0.001081959,0.006749719],"category_scores_gemma":[0.005684379,0.0005982025,0.0006770623,0.000517505,0.001794475,0.001640313,0.001322975,0.002123857,0.001077303],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001306321,"about_ca_system_score_gemma":0.001919818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003426971,"about_ca_topic_score_gemma":0.006519923,"domain_scores_codex":[0.9992112,0.0003161285,0.00005373417,0.000100082,0.0002556878,0.00006314241],"domain_scores_gemma":[0.9979942,0.001351066,0.0001562772,0.0002469936,0.0001727549,0.00007872783],"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":[0.00009262133,0.00007409706,0.0004924997,0.0001763637,0.0000248787,0.0001459938,0.0002575604,0.7572356,0.003579811,0.1765729,0.002220862,0.05912674],"study_design_scores_gemma":[0.00002269827,0.00002142736,0.00003591673,0.00002557314,0.000006792798,0.00001223307,0.00001836432,0.919943,0.001454306,0.07597709,0.00247506,0.000007546843],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005288735,0.00007858952,0.9906295,0.0001631021,0.00002312505,0.00007829276,0.0001444219,0.001160016,0.002434113],"genre_scores_gemma":[0.3212537,0.0002858556,0.6735141,0.0001364569,0.00003465522,0.0007330088,0.000551039,0.0003549987,0.003136263],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006749719,"threshold_uncertainty_score":0.02258009,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06793028415246624,"score_gpt":0.2946574244530109,"score_spread":0.2267271403005447,"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."}}