{"id":"W2574782009","doi":"","title":"Learning multi-step predictive state representations","year":2016,"lang":"en","type":"article","venue":"International Joint Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Exploit; Observable; Dynamical systems theory; Variety (cybernetics); Representation (politics); Artificial intelligence; Class (philosophy); Machine learning; State (computer science); Theoretical computer science; Algorithm","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":[0.001371508,0.0006202491,0.001093116,0.0006216106,0.0002788276,0.0009595517,0.001590307,0.001100465,0.00167513],"category_scores_gemma":[0.006714142,0.0005377377,0.0006329851,0.0007193732,0.0007303287,0.001705792,0.001195178,0.001563698,0.0004195823],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006050988,"about_ca_system_score_gemma":0.0007250327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002749326,"about_ca_topic_score_gemma":0.002880923,"domain_scores_codex":[0.9993864,0.0001821788,0.00003751553,0.000173909,0.0001579824,0.00006195703],"domain_scores_gemma":[0.9970039,0.002030876,0.0002711647,0.0003708209,0.0002559654,0.00006727035],"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":[0.00007008969,0.00004094753,0.0006183952,0.00004295928,0.00003166302,0.00004330596,0.00005015614,0.9235991,0.000848186,0.009756627,0.0005200431,0.0643786],"study_design_scores_gemma":[0.000002018633,0.000006433286,0.00002999317,0.000001752003,0.000001532695,0.000003255527,0.000001535194,0.9977883,0.000138575,0.001982671,0.00004226884,0.000001730766],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02375782,0.0001629585,0.9742882,0.000120062,0.00002244856,0.00002693007,0.00008517526,0.0007734102,0.000762929],"genre_scores_gemma":[0.846572,0.0001751971,0.1508918,0.0001266615,0.00004505664,0.0001741408,0.0003872814,0.00007705214,0.001550841],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002749326,"threshold_uncertainty_score":0.007253289,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.121939934642129,"score_gpt":0.3447195660178371,"score_spread":0.2227796313757081,"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."}}