{"id":"W1870822514","doi":"","title":"A Deeper Look at Planning as Learning from Replay","year":2015,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Bellman equation; Markov decision process; Function (biology); Temporal difference learning; Markov chain; Equivalence (formal languages); Artificial intelligence; Markov process; Machine learning; Mathematical optimization; 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":[0.001978775,0.001159294,0.001297234,0.000534215,0.0005485629,0.002275846,0.001924143,0.001976909,0.00523061],"category_scores_gemma":[0.00690223,0.0007499401,0.001492935,0.0007511142,0.003293815,0.007639389,0.002056949,0.005846545,0.0006327833],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001718156,"about_ca_system_score_gemma":0.0013174,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00485964,"about_ca_topic_score_gemma":0.002755284,"domain_scores_codex":[0.9988601,0.0004950304,0.00005330454,0.0002792756,0.0002443125,0.00006786358],"domain_scores_gemma":[0.9975576,0.001639299,0.0001836914,0.0003407713,0.0001723983,0.0001061629],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009092649,0.00006133776,0.0004556718,0.0003480221,0.00009722259,0.00008865405,0.0004295391,0.2832438,0.001912434,0.6599524,0.002114778,0.05120518],"study_design_scores_gemma":[0.00002488836,0.0001231302,0.0001431194,0.0001130011,0.00002615858,0.00006488646,0.00006658515,0.5853122,0.001084103,0.4031106,0.00988791,0.00004341671],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002378328,0.001685689,0.9908658,0.001578231,0.0001182073,0.00002177421,0.00002987386,0.0002397905,0.003082335],"genre_scores_gemma":[0.3859011,0.006757573,0.5892979,0.001945967,0.0006739963,0.0003111145,0.0001793546,0.0005136695,0.01441931],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00523061,"threshold_uncertainty_score":0.01749814,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07534542055669481,"score_gpt":0.3228219604417945,"score_spread":0.2474765398850997,"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."}}