{"id":"W4385374194","doi":"10.48550/arxiv.2307.14993","title":"Thinker: Learning to Plan and Act","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; Science and Technology Facilities Council; Université de Montréal; Dell EMC","keywords":"Plan (archaeology); Computer science; Benchmark (surveying); Reinforcement learning; Artificial intelligence; Action (physics); Interpretation (philosophy); State (computer science); Machine learning; Automated planning and scheduling; Algorithm; Programming language","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":[0.001014779,0.001359873,0.0005836608,0.0004545178,0.0003597684,0.001020415,0.002123196,0.001309627,0.007090279],"category_scores_gemma":[0.004164136,0.0006435994,0.0008134783,0.0002450716,0.001051609,0.001759626,0.001364844,0.002383254,0.001892953],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006878459,"about_ca_system_score_gemma":0.001643301,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00484627,"about_ca_topic_score_gemma":0.006388778,"domain_scores_codex":[0.9995174,0.0001576591,0.0000255164,0.0001441167,0.0001113795,0.00004392119],"domain_scores_gemma":[0.9989643,0.0005839685,0.0001039376,0.0001724686,0.00009803376,0.00007733978],"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":[0.000425117,0.0004041811,0.003077534,0.0004083072,0.000202231,0.0002253003,0.0003683479,0.5148565,0.007558876,0.06366201,0.02724572,0.3815658],"study_design_scores_gemma":[0.00008738013,0.00008985252,0.0001564808,0.00003116024,0.00002143441,0.00004674491,0.00002514835,0.9641645,0.002458182,0.02626913,0.006634326,0.0000157547],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01372242,0.0002607663,0.9655757,0.000714496,0.0001505774,0.0002097013,0.0002637126,0.00958874,0.00951397],"genre_scores_gemma":[0.2301604,0.0003159033,0.7585449,0.0005073682,0.00005730969,0.000500023,0.0007651494,0.000684252,0.008464725],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007090279,"threshold_uncertainty_score":0.02371931,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1591584466283779,"score_gpt":0.2243870914711452,"score_spread":0.06522864484276725,"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."}}