{"id":"W7124156211","doi":"10.65109/qppa8970","title":"Using spatial hints to improve policy reuse in a reinforcement learning agent","year":2010,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Reinforcement learning; Reuse; Exploit; Robustness (evolution); Task (project management); Domain (mathematical analysis); Policy learning","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":[0.00366315,0.001380668,0.001316268,0.0006463456,0.0004881083,0.0008032994,0.001679561,0.001683852,0.001397253],"category_scores_gemma":[0.01933574,0.0006030098,0.0004498346,0.0004213846,0.001474281,0.001958746,0.001604306,0.001427956,0.0003309282],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007708711,"about_ca_system_score_gemma":0.001547447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003138565,"about_ca_topic_score_gemma":0.003398456,"domain_scores_codex":[0.9983009,0.000834189,0.0001112168,0.0002814106,0.0003208876,0.0001514451],"domain_scores_gemma":[0.9883746,0.007915472,0.001206171,0.001197408,0.0007895489,0.0005168695],"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":[0.0008566962,0.0007106566,0.005617911,0.0002321952,0.00019671,0.0003810901,0.0008192048,0.8187585,0.01348318,0.00871531,0.0008595171,0.149369],"study_design_scores_gemma":[0.0001179234,0.000293232,0.0004196751,0.00002040201,0.00004558583,0.00006730393,0.00005016144,0.9851698,0.005577357,0.00755657,0.0006516459,0.00003037424],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.270315,0.0004441752,0.723934,0.000779221,0.00003969858,0.0001609753,0.00004326279,0.001598398,0.00268534],"genre_scores_gemma":[0.909992,0.00009391601,0.08867833,0.0001481309,0.00001823037,0.00007856471,0.00003363487,0.00005144019,0.0009057808],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00366315,"threshold_uncertainty_score":0.01937282,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03122750528605815,"score_gpt":0.3106378969221901,"score_spread":0.279410391636132,"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."}}