{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003650627,0.001353686,0.001282914,0.0006400989,0.0004777716,0.0007961596,0.001660962,0.001657085,0.001369744],"category_scores_gemma":[0.01931985,0.0005903257,0.0004422998,0.0004183326,0.00147692,0.001942106,0.001586238,0.001414456,0.0003200843],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007584398,"about_ca_system_score_gemma":0.001537651,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003070858,"about_ca_topic_score_gemma":0.003351312,"domain_scores_codex":[0.9983071,0.0008388276,0.0001101578,0.0002792749,0.0003142206,0.0001504378],"domain_scores_gemma":[0.9882413,0.008061459,0.001195271,0.001210737,0.0007765261,0.0005147295],"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":[0.0008586688,0.0007026162,0.005655595,0.0002333129,0.0001959662,0.0003781275,0.0008144305,0.8174877,0.01372483,0.008893254,0.0008472025,0.1502083],"study_design_scores_gemma":[0.0001159156,0.0002918693,0.0004201278,0.00002017786,0.00004531557,0.00006748961,0.00005054791,0.9852223,0.005627789,0.007463213,0.0006452534,0.00003002864],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2705413,0.0004322288,0.7237998,0.0007703025,0.00003849941,0.0001572398,0.00004257539,0.00156188,0.002656188],"genre_scores_gemma":[0.9114655,0.00009124211,0.08723393,0.000143958,0.00001797984,0.00007653336,0.00003244269,0.0000492737,0.000889132],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003650627,"threshold_uncertainty_score":0.01930654,"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."}}