{"id":"W3169292790","doi":"10.48550/arxiv.2106.06854","title":"A Deep Reinforcement Learning Approach to Marginalized Importance\\n Sampling with the Successor Representation","year":2021,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Successor cardinal; Reinforcement learning; Representation (politics); Computer science; Sampling (signal processing); Artificial intelligence; Bridge (graph theory); Variety (cybernetics); Machine learning; Simple random sample; Reinforcement; State (computer science); Mathematics; Algorithm; Sociology; Psychology; Political science; Social psychology; Detector; Law","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":[0.001681846,0.0007854383,0.001438402,0.0005330995,0.000365677,0.0008762797,0.001987396,0.001100042,0.003213346],"category_scores_gemma":[0.00621963,0.0004802041,0.0005317739,0.0005142713,0.001300317,0.001534269,0.001614762,0.002251582,0.0003866732],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001290726,"about_ca_system_score_gemma":0.001755152,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003819313,"about_ca_topic_score_gemma":0.00473607,"domain_scores_codex":[0.9992241,0.0003240522,0.0000313427,0.0001597794,0.0001712046,0.00008956096],"domain_scores_gemma":[0.9979267,0.001314666,0.0001656061,0.000214732,0.0002237556,0.0001545303],"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":[0.0001844123,0.0001463932,0.001518446,0.00009733123,0.00006473605,0.00008807822,0.00008090379,0.8349187,0.002020197,0.05701818,0.002812602,0.1010501],"study_design_scores_gemma":[0.000008751646,0.0000202023,0.00004295421,0.000004773759,0.000003630133,0.000008009202,0.000001998611,0.9905617,0.0002552954,0.008853462,0.0002363243,0.000002937524],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01310374,0.0002385687,0.9843551,0.0002507636,0.00005443101,0.00004947019,0.00005243788,0.0003900955,0.001505415],"genre_scores_gemma":[0.7612417,0.0002381732,0.2330205,0.0002966294,0.0001092598,0.0002148316,0.0002033234,0.0001324246,0.004543184],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003819313,"threshold_uncertainty_score":0.0107497,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09879524359877373,"score_gpt":0.2253305824909199,"score_spread":0.1265353388921462,"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."}}