{"id":"W6991803794","doi":"","title":"Inductive biases and generalisation for deep reinforcement learning","year":2021,"lang":"en","type":"dissertation","venue":"Oxford University Research Archive (ORA) (University of Oxford)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kellogg's (Canada)","funders":"","keywords":"Reinforcement learning; Focus (optics); Scope (computer science); Transfer of learning; Artificial neural network; Deep learning; Moment (physics); Inductive bias","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":[0.002426062,0.001227148,0.0009659193,0.0005910562,0.0003501638,0.001156691,0.001779187,0.001588646,0.004984211],"category_scores_gemma":[0.01027505,0.0006213679,0.00106197,0.000583298,0.001876912,0.002477654,0.002587567,0.004673227,0.001007433],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001976695,"about_ca_system_score_gemma":0.0009236544,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00300576,"about_ca_topic_score_gemma":0.003046444,"domain_scores_codex":[0.9989981,0.0003822399,0.00005366121,0.0002397818,0.0002359358,0.00009021975],"domain_scores_gemma":[0.9972518,0.001820811,0.0001796985,0.0003514788,0.000308505,0.00008762943],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00006014316,0.00004853741,0.0005129881,0.0001706338,0.00007235503,0.00005747954,0.0001142184,0.7700201,0.002313702,0.1174583,0.003067997,0.1061034],"study_design_scores_gemma":[0.00001037069,0.00003297271,0.00006873748,0.00002178231,0.000008233239,0.00001350609,0.000005720953,0.9204228,0.0006858868,0.07667666,0.002045364,0.000008034774],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006110196,0.0006492441,0.9876453,0.0006025795,0.00008953675,0.00005393357,0.00005681443,0.0005505065,0.004241834],"genre_scores_gemma":[0.5577418,0.001648423,0.4212341,0.001277245,0.0004446773,0.0006072313,0.0004096395,0.000641217,0.01599558],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004984211,"threshold_uncertainty_score":0.0166738,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04855249049508199,"score_gpt":0.2839006775695266,"score_spread":0.2353481870744447,"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."}}