{"id":"W2952348496","doi":"10.3389/fnbot.2018.00032","title":"Experience Replay Using Transition Sequences","year":2018,"lang":"en","type":"article","venue":"Frontiers in Neurorobotics","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Singapore University of Technology and Design; Ministry of Education - Singapore; Ministry of Education, India; University of Alberta","keywords":"Reinforcement learning; Computer science; Construct (python library); Artificial intelligence; State space; Space (punctuation); Transition (genetics); State (computer science); Function (biology); Machine learning; Algorithm","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002120106,0.0001748147,0.0001970989,0.0002207585,0.0001698621,0.0001596837,0.0009252133,0.00008333411,0.000008376611],"category_scores_gemma":[0.00009711172,0.0001848032,0.00004758926,0.0007274176,0.0002734366,0.0007845346,0.0001268499,0.0002163468,0.00001434926],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001058912,"about_ca_system_score_gemma":0.00007085866,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000178578,"about_ca_topic_score_gemma":0.000002278665,"domain_scores_codex":[0.9982489,0.0001090399,0.0003656492,0.0004729429,0.0003736048,0.0004299072],"domain_scores_gemma":[0.999028,0.00003490842,0.0001241917,0.0006445706,0.00008365687,0.00008462924],"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":[0.000009460528,0.00002255146,0.007299703,0.00001324532,0.000006899572,0.00006471065,0.004979005,0.9827315,0.001235808,0.001251279,0.001063705,0.001322181],"study_design_scores_gemma":[0.0001921277,0.00013888,0.0006872581,0.00003582695,0.000004614875,0.00003185831,0.0001757795,0.9952765,0.001944685,0.0005684123,0.0007292292,0.0002148067],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02941147,0.00003599146,0.9657541,0.0003009701,0.003600579,0.0001459069,3.48005e-7,0.0001427308,0.0006079364],"genre_scores_gemma":[0.5354649,0.0000188678,0.4637199,0.000547869,0.0001156875,0.000002926769,9.327583e-7,0.00001321657,0.0001156177],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5060535,"threshold_uncertainty_score":0.7536056,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02780311594254704,"score_gpt":0.2742440534846597,"score_spread":0.2464409375421127,"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."}}