{"id":"W4382866769","doi":"10.1609/icaps.v33i1.27238","title":"Exploration Policies for On-the-Fly Controller Synthesis: A Reinforcement Learning Approach","year":2023,"lang":"en","type":"article","venue":"Proceedings of the International Conference on Automated Planning and Scheduling","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Secretaría de Ciencia y Técnica, Universidad de Buenos Aires; International Development Research Centre; Agencia Nacional de Investigación e Innovación","keywords":"Reinforcement learning; Heuristics; Computer science; Heuristic; Task (project management); Set (abstract data type); Controller (irrigation); Supervisory control; Domain (mathematical analysis); Artificial intelligence; Space (punctuation); Control (management); Machine learning; Mathematical optimization; Mathematics; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001215197,0.0007738582,0.0008383172,0.0004703137,0.0003284004,0.0006120831,0.001454124,0.0008634132,0.001626401],"category_scores_gemma":[0.003270451,0.0005144645,0.0006277359,0.0002831573,0.001484141,0.001058631,0.001110178,0.001526866,0.000236966],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001091221,"about_ca_system_score_gemma":0.001442878,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003594031,"about_ca_topic_score_gemma":0.003708273,"domain_scores_codex":[0.9994815,0.0001953721,0.00002995954,0.0001145601,0.0001139136,0.00006481724],"domain_scores_gemma":[0.9985424,0.0009959957,0.0001390133,0.0001427819,0.0001101075,0.00006965327],"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":[0.00004026882,0.00005362025,0.0002650922,0.00005569294,0.00002323962,0.00004746066,0.00007779877,0.9485207,0.001507189,0.01649382,0.0003121725,0.03260303],"study_design_scores_gemma":[0.000008812477,0.00001630246,0.00002551992,0.000005245636,0.000003378949,0.000005867706,0.000004849945,0.9927125,0.0003093961,0.006669286,0.0002362088,0.000002739197],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008652754,0.0001097234,0.9896545,0.0001081189,0.00001154788,0.00004199181,0.0000136114,0.0002693491,0.001138269],"genre_scores_gemma":[0.5992487,0.000234686,0.3974644,0.0001505665,0.00003676685,0.0003060976,0.00006882196,0.0001370559,0.002352879],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003594031,"threshold_uncertainty_score":0.007917464,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1186295975928637,"score_gpt":0.3315998377887009,"score_spread":0.2129702401958372,"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."}}