{"id":"W4387964087","doi":"10.48550/arxiv.2310.16686","title":"Dynamics Generalisation in Reinforcement Learning via Adaptive Context-Aware Policies","year":2023,"lang":"en","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":"Division of Mathematical Sciences; Canadian Institute for Advanced Research","keywords":"Adapter (computing); Reinforcement learning; Computer science; Architecture; Artificial intelligence; Robot; Context (archaeology); Machine learning; Human–computer interaction","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004246969,0.0004136624,0.0004145099,0.0007159407,0.0002095558,0.0001815145,0.001645715,0.0003593396,0.00001564781],"category_scores_gemma":[0.00007116677,0.0005238581,0.0001562972,0.000926193,0.0001137033,0.0005039945,0.002693906,0.001161018,0.0001716889],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001352727,"about_ca_system_score_gemma":0.0002173159,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002469378,"about_ca_topic_score_gemma":0.0007139996,"domain_scores_codex":[0.9975517,0.0002477746,0.0004222273,0.0009916623,0.0002220411,0.0005646134],"domain_scores_gemma":[0.9980485,0.0001661256,0.000516705,0.0009366992,0.0002000241,0.0001319528],"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":[0.00001458467,0.00001115395,0.005034953,0.00003657587,0.00005671212,0.00010774,0.0008288207,0.8751466,0.000004607648,0.1184567,0.00005110683,0.0002504521],"study_design_scores_gemma":[0.0004300892,0.000122351,0.001986383,0.0001521842,0.00002643654,0.00000174211,0.0004978965,0.9918402,0.00002206967,0.004343479,0.00007517868,0.0005020034],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02410447,0.00001074397,0.9729246,0.0002559584,0.0006288942,0.0004323722,0.000002823377,0.0005160986,0.00112397],"genre_scores_gemma":[0.9894891,0.0001381216,0.0007988569,0.0001135348,0.00006277458,0.000003369387,0.0001163246,0.00003786135,0.009240012],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9721258,"threshold_uncertainty_score":0.9997213,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1010150129166122,"score_gpt":0.2095667935904851,"score_spread":0.1085517806738728,"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."}}