역링크

• bert_pre_training_deep_bidirectional_transformers_language_understanding
• compressive_transformer
• ctrl_conditional_transformer_language_model_controllable_generation
• hyperbolic_discounting_learning_over_multiple_horizons
• ppo_dash_improving_generalization_deep_reinforcement_learning
• proximal_policy_optimization_mixed_distributed_training
• review:2019-01_paired_open-ended_trailblazer_poet_endlessly_generating_increasingly_complex_and_diverse_learning_environments_and_their_solutions
• review:2019-03_the_lottery_ticket_hypothesis_finding_sparse_trainable_neural_networks
• review:2019-04_evolving_rewards_to_automate_reinforcement_learning
• review:2019-05_open_ended_learning_symmetric_zero_sum_games
• review:2019-10_v-mpo_on-policy_maximum_a_posteriori_policy_optimization_for_discrete_and_continuous_control
• review:2019-11_dd-ppo_learning_near-perfect_pointgoal_navigators_from_2.5_billion_frames
• review:2019-11_textworld_a_learning_environment_for_text-based_games
• review:2019-12_covariance_matrix_adaptation_for_the_rapid_illumination_of_behavior_space
• review:language_models_are_unsupervised_multitask_learners
• strategies_structuring_story_generation