{"id":"W4291821302","doi":"10.32470/ccn.2022.1229-0","title":"Continual Reinforcement Learning with Multi-Timescale Successor Features","year":2022,"lang":"en","type":"article","venue":"2022 Conference on Cognitive Computational Neuroscience","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Successor cardinal; Reinforcement learning; Reinforcement; Computer science; Artificial intelligence; Engineering; Structural engineering; Mathematics","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":[0.001238374,0.0004608193,0.0006214749,0.0002970726,0.0002783065,0.0006630088,0.001054583,0.0007784078,0.00475613],"category_scores_gemma":[0.006136955,0.0003212812,0.0003567203,0.000278137,0.0006412935,0.001513341,0.001274983,0.001755552,0.0003767675],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000436192,"about_ca_system_score_gemma":0.0006334109,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009484216,"about_ca_topic_score_gemma":0.001370999,"domain_scores_codex":[0.9996407,0.00008544232,0.00002472354,0.00009949791,0.0001016134,0.00004799558],"domain_scores_gemma":[0.9976341,0.001451205,0.0001864014,0.0002952297,0.000228365,0.0002048367],"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":[0.0008761854,0.0005604589,0.002684043,0.0001901382,0.0001134702,0.000272718,0.0001427251,0.6576232,0.01223369,0.05837278,0.002556694,0.2643739],"study_design_scores_gemma":[0.00002229582,0.00006529065,0.0001720814,0.000004478534,0.000006936383,0.00002723898,0.000003967409,0.987493,0.0005785338,0.01139987,0.0002202858,0.000005973539],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1424069,0.000380914,0.8477125,0.0005105748,0.0002078372,0.00008606407,0.00008560378,0.0007800519,0.007829497],"genre_scores_gemma":[0.9720652,0.00005599924,0.02559723,0.00004808868,0.00002620982,0.00005122843,0.00002764995,0.00003075217,0.0020977],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00475613,"threshold_uncertainty_score":0.0159108,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0353669370020116,"score_gpt":0.2839279176125578,"score_spread":0.2485609806105462,"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."}}