{"id":"W2925234320","doi":"10.48550/arxiv.1903.09762","title":"TTR-Based Reward for Reinforcement Learning with Implicit Model Priors","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Reinforcement learning; Computer science; Key (lock); Function (biology); Inefficiency; Artificial intelligence; Process (computing); Exploit; Temporal difference learning; State (computer science); Machine learning; Algorithm","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":[0.002017498,0.001143287,0.001335171,0.0005121175,0.0003997674,0.0008710999,0.00164401,0.001182582,0.003222883],"category_scores_gemma":[0.009917859,0.0004597312,0.000568279,0.0004763926,0.001359776,0.001685748,0.001356944,0.002020187,0.0005051074],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001524106,"about_ca_system_score_gemma":0.001900693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004499862,"about_ca_topic_score_gemma":0.003702425,"domain_scores_codex":[0.9990853,0.0003482643,0.00004740581,0.000171101,0.0002381313,0.0001098138],"domain_scores_gemma":[0.996606,0.00236047,0.0002947694,0.0002937109,0.0003178653,0.0001271354],"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":[0.0000768969,0.00005702032,0.0002925696,0.00004977619,0.00001819919,0.00003330069,0.00002746793,0.9613335,0.0007322849,0.01365008,0.000646889,0.02308215],"study_design_scores_gemma":[0.000006704962,0.00001408742,0.00002160116,0.000002607833,0.00000212565,0.000004051478,0.000001043266,0.9961392,0.0001900894,0.003521166,0.000094759,0.000002450956],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01160518,0.0001476749,0.9858348,0.0001488879,0.00002919312,0.00004182606,0.00003674917,0.0006110754,0.001544601],"genre_scores_gemma":[0.8449294,0.0001417946,0.1517755,0.0001777217,0.00003610402,0.0001951353,0.0001428289,0.0001843803,0.002417254],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004499862,"threshold_uncertainty_score":0.01105821,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06577840482045562,"score_gpt":0.198769425024594,"score_spread":0.1329910202041384,"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."}}