{"id":"W4285061979","doi":"","title":"Graph augmented Deep Reinforcement Learning in the GameRLand3D environment","year":2021,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ubisoft (Canada)","funders":"","keywords":"Reinforcement learning; Graph; Computer science; Artificial intelligence; Reinforcement; Theoretical computer science; Psychology; Social psychology","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":[0.0004833837,0.001201335,0.0006718622,0.0003070462,0.00039346,0.0008228586,0.001415067,0.001276771,0.002781281],"category_scores_gemma":[0.001870819,0.0004263021,0.0006039686,0.0002897351,0.001074825,0.0009673638,0.001391491,0.001544586,0.000531634],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00119608,"about_ca_system_score_gemma":0.0012696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02025831,"about_ca_topic_score_gemma":0.02536617,"domain_scores_codex":[0.9997072,0.00009995134,0.00000780069,0.00008339397,0.00005447746,0.00004727301],"domain_scores_gemma":[0.999569,0.0002470585,0.00002890571,0.00006062784,0.00004543254,0.00004893533],"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":[0.0000950826,0.00005358627,0.0003100826,0.000049914,0.00002124688,0.00009783662,0.00003509508,0.974686,0.001271475,0.003499425,0.001676583,0.01820365],"study_design_scores_gemma":[0.00001609676,0.00002380104,0.00006082105,0.000003744567,0.000002455803,0.000008612114,0.000006516593,0.9954447,0.0006535625,0.003096548,0.0006788594,0.000004271114],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1533492,0.0007786279,0.8215376,0.0009624886,0.0001959686,0.0001658853,0.0009706964,0.01055461,0.01148493],"genre_scores_gemma":[0.7759751,0.0001964853,0.2176684,0.000283519,0.00002175843,0.0001731161,0.0009088073,0.0004451859,0.004327682],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02025831,"threshold_uncertainty_score":0.04028076,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01290767516935561,"score_gpt":0.2150617302733661,"score_spread":0.2021540551040105,"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."}}