{"id":"W4200140111","doi":"10.1109/iros51168.2021.9636140","title":"Memory-based Deep Reinforcement Learning for POMDPs","year":2021,"lang":"en","type":"article","venue":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":77,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Compute Canada","keywords":"Reinforcement learning; Markov decision process; Computer science; Observable; Artificial intelligence; Partially observable Markov decision process; Noise (video); Robotics; Component (thermodynamics); Sensitivity (control systems); Feature (linguistics); Deep learning; Markov process; Markov chain; Machine learning; Robot; Markov model","routes":{"ca_aff":true,"ca_fund":true,"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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006089497,0.0003845506,0.0004267824,0.0002573772,0.0003221998,0.001183694,0.0009288816,0.0001613365,0.0003615584],"category_scores_gemma":[0.0002997071,0.0003683124,0.0001928463,0.0002311891,0.00006208236,0.0003371157,0.0002204989,0.0003973161,0.0001564546],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002457155,"about_ca_system_score_gemma":0.0002982534,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004893216,"about_ca_topic_score_gemma":0.000009288976,"domain_scores_codex":[0.9966825,0.0001668484,0.0008429089,0.0008342643,0.0009750873,0.0004984342],"domain_scores_gemma":[0.9973763,0.0003893904,0.0004287966,0.0005852306,0.0009940602,0.0002262096],"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":[0.00002349043,0.00005643287,0.0001786687,0.00007794801,0.0001241519,0.0000301013,0.0004081693,0.8524416,0.0009895745,0.141848,0.0004786097,0.003343312],"study_design_scores_gemma":[0.0006008809,0.0003026774,0.00003606673,0.0003179113,0.0000212551,0.00002571889,0.000412215,0.9767465,0.005107411,0.0002010448,0.01582596,0.0004023609],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004599668,0.0001548914,0.9808946,0.001263474,0.003897588,0.0005399879,0.000003304895,0.0001304537,0.01265576],"genre_scores_gemma":[0.9750868,0.0003226251,0.006820627,0.000640633,0.000432514,0.0001995422,0.000141524,0.00003751478,0.01631819],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9746268,"threshold_uncertainty_score":0.9998769,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06087323939367912,"score_gpt":0.3000001409251943,"score_spread":0.2391269015315152,"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."}}