{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001188427,0.000874077,0.0005623295,0.0001898756,0.0002067587,0.000484573,0.0008350508,0.0007545225,0.001245845],"category_scores_gemma":[0.003772844,0.0003545614,0.0002948357,0.0001208786,0.0006773521,0.0006531021,0.000964504,0.001340005,0.0002392168],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004646938,"about_ca_system_score_gemma":0.0007138753,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002342617,"about_ca_topic_score_gemma":0.002697761,"domain_scores_codex":[0.9996806,0.0001352539,0.00001777253,0.00006912813,0.00005652306,0.00004077553],"domain_scores_gemma":[0.9987986,0.0007496646,0.000136333,0.0001080012,0.0001181262,0.00008925907],"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":[0.0002292448,0.00009841019,0.0008996407,0.00007604609,0.00005004672,0.00009011717,0.0001147308,0.9381865,0.006278649,0.003221983,0.0005950988,0.05015957],"study_design_scores_gemma":[0.00001105504,0.00005785179,0.00008354646,0.000004582972,0.000003402509,0.00001104462,0.000005497982,0.9975183,0.0009151389,0.001227395,0.0001582068,0.000003930303],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09961428,0.0004242311,0.8963079,0.0002155427,0.00004945361,0.00006041118,0.00002333173,0.0009850294,0.002319815],"genre_scores_gemma":[0.923681,0.00008398636,0.07415709,0.0001022658,0.00001373783,0.00007132263,0.00003316842,0.00007389468,0.001783425],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002342617,"threshold_uncertainty_score":0.006285071,"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."}}