{"id":"W3131011999","doi":"","title":"Memory-based Deep Reinforcement Learning for POMDP.","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Partially observable Markov decision process; Reinforcement learning; Computer science; Markov decision process; Observable; Artificial intelligence; Component (thermodynamics); Noise (video); Feature engineering; Process (computing); Robotics; Feature (linguistics); Machine learning; Deep learning; Markov process; Markov chain; Markov model; Robot; Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004496168,0.0004763023,0.0004887805,0.0003363212,0.0003738562,0.0004336127,0.002267795,0.0003836268,0.00009136282],"category_scores_gemma":[0.0002053915,0.0005998844,0.0004776801,0.0005639443,0.00009036101,0.0004115334,0.002132246,0.0007412893,0.00005626447],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004526261,"about_ca_system_score_gemma":0.0005471152,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005713427,"about_ca_topic_score_gemma":0.00001202614,"domain_scores_codex":[0.9971863,0.0001756271,0.0003847525,0.001366119,0.0002272303,0.0006599824],"domain_scores_gemma":[0.9968781,0.0002941323,0.0005437947,0.001619083,0.0004362953,0.0002285834],"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":[0.00002327947,0.00002711596,0.0003078982,0.0001925547,0.0001104039,0.0001251306,0.0002436619,0.9853114,0.0000343117,0.01312342,0.0001067821,0.0003940685],"study_design_scores_gemma":[0.000926878,0.0001513637,0.00005904367,0.0001498726,0.00009206356,0.000001956771,0.0001536456,0.9952304,0.0005944819,0.0004784782,0.001528576,0.0006332674],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004255331,0.00005189459,0.9901015,0.0001311096,0.0009619077,0.0006587199,7.95083e-7,0.0004497361,0.003389032],"genre_scores_gemma":[0.9745155,0.00005227962,0.01761484,0.0002903337,0.00009758682,0.000006522434,0.0001481945,0.00004185659,0.007232896],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9724866,"threshold_uncertainty_score":0.9996452,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06249373525342344,"score_gpt":0.1985731635025601,"score_spread":0.1360794282491367,"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."}}