{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001340779,0.0006395687,0.0006064167,0.001651147,0.0003026846,0.0005338853,0.002588277,0.0004623015,0.00004634139],"category_scores_gemma":[0.00009318029,0.0006480951,0.0001731434,0.00101638,0.0003498657,0.0009976637,0.0008313095,0.002053075,0.0002197125],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009123244,"about_ca_system_score_gemma":0.0005821707,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006064984,"about_ca_topic_score_gemma":0.0001069893,"domain_scores_codex":[0.9951957,0.00008782197,0.0009030528,0.001636287,0.00124888,0.0009281954],"domain_scores_gemma":[0.9977198,0.0003250504,0.0002434968,0.001342426,0.0002134414,0.0001557735],"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":[0.000005390459,0.00001571661,0.000107788,0.00003678577,0.000009365505,0.00002568175,0.0008364464,0.9389929,0.0004284133,0.005867062,0.000002432966,0.05367207],"study_design_scores_gemma":[0.0005853624,0.0003401434,0.0002133283,0.0004201494,0.000007925979,0.00003443272,3.262828e-7,0.9930965,0.0003646837,0.002254692,0.001979393,0.0007031068],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00003908031,0.0001322201,0.9926314,0.0002673783,0.001943761,0.0007470354,4.618864e-7,0.0002275612,0.004011044],"genre_scores_gemma":[0.6094308,0.0002234053,0.3803879,0.001125754,0.0002962424,0.00002970474,0.00002776054,0.0001010119,0.008377407],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6122435,"threshold_uncertainty_score":0.999597,"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."}}