{"id":"W4287251902","doi":"10.48550/arxiv.2103.15793","title":"LASER: Learning a Latent Action Space for Efficient Reinforcement\\n Learning","year":2021,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Reinforcement learning; Action (physics); Computer science; Artificial intelligence; Space (punctuation); Task (project management); Machine learning; Engineering; Physics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00142163,0.0009244874,0.0009235488,0.0004284797,0.0004104774,0.0009205035,0.002030806,0.001483776,0.005121836],"category_scores_gemma":[0.005176137,0.0007280501,0.0007098967,0.0003791965,0.001319561,0.001413843,0.002225843,0.002883279,0.001177366],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001127357,"about_ca_system_score_gemma":0.002010947,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006733193,"about_ca_topic_score_gemma":0.009060289,"domain_scores_codex":[0.9993814,0.0002216596,0.0000268859,0.0001577236,0.0001418405,0.00007036905],"domain_scores_gemma":[0.9987783,0.0007328247,0.0001044061,0.0001691256,0.0001120509,0.0001032686],"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":[0.0001586309,0.0001164288,0.0009181312,0.0001243689,0.00006228341,0.00008867213,0.0001221072,0.8594728,0.005008822,0.01725709,0.003475714,0.113195],"study_design_scores_gemma":[0.00001207754,0.00001794167,0.0000379066,0.000004841437,0.000002191161,0.000006556257,0.000003995383,0.9948629,0.0005725186,0.004136514,0.000339171,0.000003489964],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007333932,0.000130263,0.9897255,0.0001644115,0.00002546498,0.00004583779,0.00007798007,0.001644441,0.0008520964],"genre_scores_gemma":[0.4932061,0.0002060323,0.4998781,0.0003558899,0.00005604902,0.0005585207,0.0005654481,0.0006091591,0.004564767],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006733193,"threshold_uncertainty_score":0.01713419,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0890968772339231,"score_gpt":0.2143847517416132,"score_spread":0.1252878745076901,"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."}}