{"id":"W2945090640","doi":"10.1007/978-3-030-18305-9_18","title":"Options in Multi-task Reinforcement Learning - Transfer via Reflection","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Reinforcement learning; Regret; Computer science; Transfer of learning; Artificial intelligence; Context (archaeology); State space; Task (project management); Landmark; Formalism (music); Reflection (computer programming); Machine 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":[0.001753728,0.0007977373,0.0009882126,0.0002458922,0.00036328,0.001011226,0.001728501,0.001483279,0.005195679],"category_scores_gemma":[0.004960645,0.0004580801,0.0006955728,0.0003584549,0.001679987,0.002459828,0.002590037,0.002656241,0.0006343377],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006500848,"about_ca_system_score_gemma":0.0005616958,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001167436,"about_ca_topic_score_gemma":0.0007221987,"domain_scores_codex":[0.9992753,0.0003848994,0.00003725705,0.0001297496,0.00009979532,0.00007302462],"domain_scores_gemma":[0.9979234,0.001603296,0.00008574239,0.0001886012,0.0001027498,0.00009613761],"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":[0.0004319732,0.0001694013,0.0003816362,0.000205259,0.00007878041,0.0001368025,0.0002638124,0.6049759,0.003784622,0.2120834,0.002000564,0.1754879],"study_design_scores_gemma":[0.00003095608,0.0000685684,0.00005591199,0.00001346815,0.000008358162,0.0000184342,0.00001462857,0.8880473,0.0007803703,0.110413,0.0005381457,0.00001087207],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01584103,0.0003425333,0.9777449,0.0002159652,0.00006177518,0.00004035713,0.00001912724,0.000320072,0.005414331],"genre_scores_gemma":[0.8353031,0.0003110339,0.1540966,0.0001168899,0.00005467741,0.0002668565,0.00005636354,0.0001523253,0.009642147],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005195679,"threshold_uncertainty_score":0.01738125,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0295807504559548,"score_gpt":0.2728307023066546,"score_spread":0.2432499518506998,"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."}}