{"id":"W4364304082","doi":"10.1109/raai56146.2022.10092979","title":"Addressing Different Goal Selection Strategies In Hindsight Experience Replay With Actor-Critic Methods For Robotic Hand Manipulation","year":2022,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Hindsight bias; Reinforcement learning; Computer science; Task (project management); Artificial intelligence; Selection (genetic algorithm); Robot; Block (permutation group theory); Binary number; Machine learning; Human–computer interaction; Engineering; 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":[],"consensus_categories":[],"category_scores_codex":[0.000354343,0.0001641089,0.0001889949,0.0001895204,0.0005097333,0.0005719823,0.0004256767,0.00003502362,0.0000627222],"category_scores_gemma":[0.00005041639,0.0001380017,0.0000360388,0.0004301864,0.00004257873,0.0009109335,0.0001802457,0.0002257462,6.766468e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002590508,"about_ca_system_score_gemma":0.00008912792,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004810476,"about_ca_topic_score_gemma":0.00003455087,"domain_scores_codex":[0.9983791,0.0002429991,0.0002942633,0.0004346597,0.0003207083,0.0003283033],"domain_scores_gemma":[0.9992156,0.0002654097,0.0001257942,0.0002879926,0.00005699821,0.00004817829],"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":[0.00002595896,0.00003017911,0.002204168,0.00002342157,0.000007669717,0.000002237836,0.002825384,0.9713376,0.005864744,0.01591934,0.00001438959,0.00174495],"study_design_scores_gemma":[0.0004579928,0.0003912516,0.007867835,0.00002399891,0.000006960072,0.00002284317,0.001014623,0.9841365,0.00516673,0.0005797367,0.000125464,0.0002061183],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04893246,0.00002382451,0.9498071,0.0001036352,0.0002891981,0.0003842259,1.026559e-7,0.0001166933,0.0003427345],"genre_scores_gemma":[0.7872183,7.941233e-7,0.2120869,0.00005122741,0.00002087928,0.0001627841,0.000005955964,0.0000117186,0.0004415166],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7382858,"threshold_uncertainty_score":0.5627545,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07996687853250528,"score_gpt":0.373707120529135,"score_spread":0.2937402419966297,"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."}}