{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001780757,0.001139255,0.0008978405,0.000637453,0.0004845402,0.0008432436,0.001211102,0.001036274,0.002461264],"category_scores_gemma":[0.01461323,0.0005397965,0.0005819072,0.0003970815,0.001010733,0.002210734,0.001525544,0.001553416,0.0006137184],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000549831,"about_ca_system_score_gemma":0.0007214748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001734281,"about_ca_topic_score_gemma":0.001672566,"domain_scores_codex":[0.9988239,0.0004526433,0.00008447748,0.0002850367,0.0002608179,0.00009314696],"domain_scores_gemma":[0.9947886,0.002592608,0.0006284175,0.001182632,0.0005732214,0.0002344778],"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":[0.001214293,0.0003508926,0.005455814,0.0003094264,0.0001549677,0.0004277726,0.000692432,0.642372,0.022701,0.02061427,0.002023101,0.3036841],"study_design_scores_gemma":[0.00007622706,0.0005286619,0.0009585816,0.00004809135,0.00003766638,0.00020861,0.00008430897,0.9637264,0.01317525,0.01769249,0.003419836,0.00004390006],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07451227,0.0003986396,0.9213085,0.0001940304,0.00006841452,0.0001534935,0.00008087751,0.001480022,0.001803802],"genre_scores_gemma":[0.8387589,0.0001798524,0.1585635,0.0001142593,0.00002723191,0.000235866,0.0002111787,0.0001222073,0.001787004],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002461264,"threshold_uncertainty_score":0.009417713,"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."}}