今天查阅资料，随手翻阅，发现近两年内也阅读了一些技术文章，良莠都有，也算是兼容并包了。做了简短整理，罗列如下。为自己加油，为自己喝彩。

调度优化类
Real-world_Ride-hailing_Vehicle_Repositioning_using_Deep_Reinforcement_Learning.2021.pdf
Scalable_Deep_Reinforcement_Learning_for_Ride-Hailing.2020.pdf
Deep_Reinforcement_Learning_for_Ride-sharing_Dispatching_and_Repositioning.pdf
Ride-hailing_Order_Dispatching_at_DiDi_via_Reinforcement_Learning.pdf

游戏对抗类：
Rethinking_of_AlphaStar.2021.pdf
An_Introduction_of_mini-AlphaStar.2021.pdf
Suphx_Mastering_Mahjong_with_Deep_Reinforcement_Learning.2020.pdf
Agent57_Outperforming_the_Atari_Human_Benchmark.2020.pdf
Mastering_Atari_Go_Chess_and_Shogi_by_Planning_with_a_Learned_Model.MuZero.2020.pdf
Hide-and-Seek_A_Template_for_Explainable_AI.2020.pdf
Emergent_Tool_Use_From_Multi-Agent_Autocurricula.2019.pdf
Mastering_Chess_and_Shogi_by_Self-Play_with_a_General_Reinforcement_Learning_Algorithm.2017.pdf
Grandmaster_level_in_StarCraft_II_using_multi-agent_reinforcement_learning.2019.pdf
Dota_2_with_Large_Scale_Deep_Reinforcement_Learning.2019.pdf
Long-Term_Planning_and_Situational_Awareness_in_OpenAI_Five.2019.pdf
Mastering_Complex_Control_in_MOBA_Games_with_Deep_Reinforcement_Learning.2020.pdf
Superhuman_AI_for_multiplayer_poker.2019.pdf
SCC_an_Efficient_Deep_Reinforcement_Learning_Agent_Mastering_the_Game_of_StarCraft_II.2021.pdf
Learning_to_Draft_in_MOBA_Games_with_Neural_Networks_and_Tree_Search.2021.pdf
Towards_Playing_Full_MOBA_Games_with_Deep_Reinforcement_Learning.2020.pdf
Learning_Diverse_Policies_in_MOBA_Games_via_Macro-Goals.2021.pdf
DeepStack_Expert-Level_Artificial_Intelligence_in_Heads-Up_No-Limit_Poker.2017

决策算法类
The_Surprising_Effectiveness_of_MAPPO_in_Cooperative_Multi-Agent_Games.2021.pdf
Multi-Agent_Actor-Critic_for_Mixed_Cooperative-Competitive_Environments.MADDPG.2020.pdf
Addressing_Function_Approximation_Error_in_Actor-Critic_Methods.TD3.2018.pdf
Counterfactual_Multi-Agent_Policy_Gradients.COMA.2017.pdf
The_Reactor_A_fast_and_sample-efficient_Actor-Critic_agent_for_Reinforcement_Learning.2018.pdf
QMIX_Monotonic_Value_Function_Factorisation_for_Deep_Multi-Agent_Reinforcement_Learning.2018.pdf
Proximal_Policy_Gradient_PPO_with_Policy_Gradient.2020.pdf
The_Surprising_Effectiveness_of_PPO_in_Cooperative_Multi-Agent_Games.2021

DREAM_Deep_Regret_Minimization_with_Advantage_Baselines_and_Model-free_Learning.2020.pdf
Solving_Imperfect-Information_Games_via_exponential_counterfactual_regret_minimization.2020.pdf
Solving_Imperfect-Information_Games_via_Discounted_Regret_Minimization.2019.pdf
Single_Deep_Counterfactual_Regret_Minimization.2019.pdf
Deep_Counterfactual_Regret_Minimization.2019.pdf

综述理论类
On_the_Opportunities_and_Risks_of_Foundation_Models.2021.pdf
The_Principles_of_Deep_Learning_Theory.2021.pdf
A_Survey_on_Multi-modal_Summarization.2021.pdf
A_Comprehensive_Survey_and_Performance_Analysis_of_Activation_Functions_in_Deep_Learning.2021.pdf
Gathering_Strength_Gathering_Storms.AI100.2021.pdf
Artificial_intelligence_and_life_in_2030.AI100.2016.pdf
An_Introduction_to_Counterfactual_Regret_Minimization.2013.pdf
A_Survey_and_Critique_of_Multiagent_Deep_Reinforcement_Learning.2019.pdf
Pre-trained_Models_for_Natural_Language_Processing_A_Survey.2020
Reward_is_enough.2021.pdf
Discovering_Reinforcement_Learning_Algorithms.2021.pdf
Pre-Trained_Models_Past_Present_and_Future.2021.pdf
GPT_Understands_Too.2021.pdf
Inductive_Biases_for_Deep_Learning_of_Higher-Level_Cognition.2021.pdf
Multi-Agent_Reinforcement_Learning_A_Selective_Overview_of_Theories_and_Algorithms.2019
Real_World_Games_Look_Like_Spinning_Tops.2020.pdf
Time_and_Space_Why_Imperfect_Information_Games_are_Hard.2017.pdf
Survey_of_self-play_in_reinforcement_learning.2021.pdf

自然语言处理类
All_NLP_Tasks_Are_Generation_Tasks_A_General_Pretraining_Framework.2021.pdf
Language_Models_are_Few-Shot_Learners.GPT-3.2020.pdf
Language_Models_are_Unsupervised_Multitask_Learners.GPT-2.pdf
Improving_Language_Understanding_by_Generative_Pre-Training.GPT.pdf
BERT.Pre-training_of_Deep_Bidirectional_Transformers_for_Language_Understanding.2019.pdf
Unified_Language_Model_Pre-training_for_Natural_Language_Understanding_and_Generation.2019
Attention_Is_All_You_Need.2017.pdf

多模态相关
CogView_Mastering_Text-to-Image_Generation_via_Transformers.2021
Zero-Shot_Text-to-Image_Generation.DALL-E.2021.pdf
Learning_Transferable_Visual_Models_From_Natural_Language_Supervision.CLIP.2021.pdf
WenLan_Bridging_Vision_and_Language_by_Large-Scale_Multi-Modal_Pre-Training.2021
A_Chinese_Multi-Modal_Pretrainer.m6.2021.pdf

其他
FastMoE.a_Fast_Mixture-of-Expert_Training_System.2021.pdf
Population_Based_Training_of_Neural_Networks.2017.pdf