{"id":"W2902729397","doi":"10.1613/jair.1.11263","title":"Grounding Language for Transfer in Deep Reinforcement Learning","year":2018,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Regina","funders":"","keywords":"Reinforcement learning; Computer science; Variety (cybernetics); Transfer of learning; Representation (politics); Artificial intelligence; Task (project management); Differentiable function; Domain (mathematical analysis); Component (thermodynamics); Meaning (existential); Machine learning","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":[0.0015388,0.000822863,0.0006731302,0.0003128105,0.0003187484,0.0009020603,0.001455251,0.0009878164,0.003869926],"category_scores_gemma":[0.008419376,0.0003767623,0.0004645805,0.0003237191,0.001615824,0.002792707,0.001638919,0.00228585,0.0006117422],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001166476,"about_ca_system_score_gemma":0.001001064,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002177422,"about_ca_topic_score_gemma":0.002020562,"domain_scores_codex":[0.9993768,0.0002712831,0.00003212376,0.000157309,0.0001059309,0.00005657274],"domain_scores_gemma":[0.9978663,0.001466484,0.00019536,0.0002575567,0.0001456883,0.00006858312],"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":[0.0001057424,0.0001197023,0.0005512286,0.0001001776,0.00002803802,0.0001357105,0.000220332,0.859905,0.00339498,0.07762755,0.001225425,0.05658612],"study_design_scores_gemma":[0.000009332321,0.00002929068,0.00002881457,0.000007184947,0.000003341387,0.000008356428,0.000008064091,0.9723651,0.0006973583,0.02629643,0.0005424908,0.000004216641],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01679389,0.0001259852,0.979665,0.0003685812,0.0000445777,0.00004646293,0.00005348457,0.0007189062,0.002183159],"genre_scores_gemma":[0.8872722,0.0001346256,0.1086542,0.0002729237,0.00003913224,0.0002487676,0.0001310886,0.000143729,0.003103318],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003869926,"threshold_uncertainty_score":0.01294619,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1503297529386259,"score_gpt":0.4297375410971567,"score_spread":0.2794077881585307,"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."}}