{"id":"W2159666783","doi":"10.5555/1838206.1838251","title":"Using spatial hints to improve policy reuse in a reinforcement learning agent","year":2010,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Reinforcement learning; Reuse; Computer science; Exploit; Robustness (evolution); Task (project management); Domain (mathematical analysis); Artificial intelligence; Human–computer interaction; Machine learning; Data science; Computer security; Engineering; Systems engineering","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":[0.0005037087,0.0001939509,0.0001832133,0.0004541989,0.0001253648,0.0002555751,0.001353753,0.00009246491,0.0001062146],"category_scores_gemma":[0.0009272161,0.0001857412,0.0000466648,0.0006063385,0.00002586688,0.0004031426,0.001487752,0.0005593477,0.0002752883],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002120877,"about_ca_system_score_gemma":0.0002113959,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003164559,"about_ca_topic_score_gemma":0.0001517297,"domain_scores_codex":[0.9980642,0.00004892088,0.0004329074,0.0004311276,0.0004548307,0.0005679854],"domain_scores_gemma":[0.9984468,0.00005388235,0.0001315402,0.001073971,0.00007915369,0.0002147201],"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":[0.000005873333,0.00001286828,0.001372985,0.000006928666,0.00000642409,0.00001146975,0.001092765,0.942968,0.04108759,0.008100243,0.00008306024,0.005251816],"study_design_scores_gemma":[0.0004010066,0.0001942903,0.001474269,0.00001928093,0.000002287066,0.000006467149,0.00002424336,0.9859486,0.006033171,0.0001284243,0.005505276,0.0002627283],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07614447,9.101863e-7,0.914462,0.0008018592,0.0006951335,0.0003306043,7.870811e-8,0.0001588681,0.007406059],"genre_scores_gemma":[0.8621309,0.00000164151,0.1332581,0.0007402907,0.0001774937,0.00001140706,0.000001196725,0.00001591719,0.003663077],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7859864,"threshold_uncertainty_score":0.7574307,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02532803722935456,"score_gpt":0.3020450763178422,"score_spread":0.2767170390884877,"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."}}