{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009706444,0.0009859692,0.001040051,0.0003768428,0.000331804,0.0005718733,0.001256398,0.000897947,0.00292607],"category_scores_gemma":[0.003432118,0.0004798787,0.000546721,0.0003745072,0.0007889193,0.0009332053,0.001206668,0.001987369,0.0003928727],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001378065,"about_ca_system_score_gemma":0.001665443,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008988316,"about_ca_topic_score_gemma":0.01001556,"domain_scores_codex":[0.9996815,0.00008853037,0.00002207885,0.00007597838,0.00007213933,0.00005988271],"domain_scores_gemma":[0.9985826,0.0009648756,0.0001318536,0.00008975905,0.0001510519,0.00007982056],"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":[0.00006422248,0.00005803062,0.0006251471,0.00009582262,0.00003489961,0.00004468136,0.00003748555,0.9450417,0.0006170596,0.00746083,0.001065669,0.04485448],"study_design_scores_gemma":[0.000004937508,0.00001146947,0.00002260663,0.000003179852,0.000002356687,0.000003539041,0.000001905928,0.9968353,0.0001456728,0.002834585,0.0001329819,0.000001453201],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0163102,0.0005681406,0.9792322,0.0002768928,0.00007654698,0.00005808473,0.0001157396,0.0009474759,0.002414826],"genre_scores_gemma":[0.8667476,0.0002881256,0.1298195,0.0002272539,0.00003483304,0.0002121166,0.0002527591,0.00009711352,0.002320653],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008988316,"threshold_uncertainty_score":0.01787204,"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."}}