{"id":"W2737821837","doi":"10.1109/icra.2017.7989686","title":"Adapting learned robotics behaviours through policy adjustment","year":2017,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Robot; Computer science; Inverted pendulum; Task (project management); Artificial intelligence; Robotics; Action (physics); State space; Physical system; Mobile robot; Control theory (sociology); Control (management); 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":[0.001250139,0.0009294722,0.000697232,0.0004594603,0.0003228299,0.000652199,0.00144441,0.0009563544,0.001616711],"category_scores_gemma":[0.007334785,0.0005260698,0.0005217111,0.0003032181,0.001355233,0.00101404,0.001143177,0.00158461,0.0004124321],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007536882,"about_ca_system_score_gemma":0.0008674457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002510527,"about_ca_topic_score_gemma":0.001950024,"domain_scores_codex":[0.9992169,0.0002389528,0.00004663028,0.0002098688,0.0002000822,0.00008753215],"domain_scores_gemma":[0.9978399,0.001047791,0.0003433719,0.0004320102,0.0002391512,0.00009779315],"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":[0.00007171124,0.0001193429,0.001206481,0.00005564483,0.00005904197,0.0000855354,0.0001299541,0.930478,0.006492409,0.006112771,0.0005003175,0.05468886],"study_design_scores_gemma":[0.00001461253,0.00004291062,0.0001400387,0.000005334258,0.000007191966,0.00001891359,0.000009808209,0.9936162,0.001360832,0.004319062,0.0004568775,0.000008203424],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03520818,0.00009411245,0.9611998,0.0001727724,0.00004285259,0.00007953402,0.00001749395,0.0009585957,0.002226622],"genre_scores_gemma":[0.8973403,0.00009127864,0.100282,0.0001887683,0.00003154175,0.0001768445,0.00004645157,0.0001195134,0.001723356],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002510527,"threshold_uncertainty_score":0.006611407,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07174920135323527,"score_gpt":0.3402462901202425,"score_spread":0.2684970887670072,"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."}}