Deep-Reinforcement-Learning-Papers

awesome deep learning papers for reinforcement learning

---

一. First Start : DQN

• [1. Playing Atari with Deep Reinforcement Learning，V. Mnih et al., NIPS Workshop, 2013.]

• [2. Human-level control through deep reinforcement learning, V. Mnih et al., Nature, 2015.]

二. DQN的各種改進版本(注重算法上的改進)

• [1. Dueling Network Architectures for Deep Reinforcement Learning. Z. Wang et al., arXiv, 2015.]

• [2. Prioritized Experience Replay, T. Schaul et al., ICLR, 2016.]

• [3. Deep Reinforcement Learning with Double Q-learning, H. van Hasselt et al., arXiv, 2015.]

• [4. Increasing the Action Gap: New Operators for Reinforcement Learning, M. G. Bellemare et al., AAAI, 2016.]

• [5. Dynamic Frame skip Deep Q Network, A. S. Lakshminarayanan et al., IJCAI Deep RL Workshop, 2016.]

• [6. Deep Exploration via Bootstrapped DQN, I. Osband et al., arXiv, 2016.]

• [7. How to Discount Deep Reinforcement Learning: Towards New Dynamic Strategies, V. François-Lavet et al., NIPS Workshop, 2015.]

• [8. Learning functions across many orders of magnitudes，H Van Hasselt，A Guez，M Hessel，D Silver]

• [9. Massively Parallel Methods for Deep Reinforcement Learning, A. Nair et al., ICML Workshop, 2015.]

• [10. State of the Art Control of Atari Games using shallow reinforcement learning]

• [11. Learning to Play in a Day: Faster Deep Reinforcement Learning by Optimality Tightening]

• [12. Deep Reinforcement Learning with Averaged Target DQN]

• [13. Safe and Efficient Off-Policy Reinforcement Learning]

• [14. The Predictron: End-To-End Learning and Planning ]

三. DQN的各種改進版本（注重於模型的改進）

• [1. Deep Recurrent Q-Learning for Partially Observable MDPs, M. Hausknecht and P. Stone, arXiv, 2015.]

• [2. Deep Attention Recurrent Q-Network]

• [3. Control of Memory, Active Perception, and Action in Minecraft, J. Oh et al., ICML, 2016.]

• [4. Progressive Neural Networks]

• [5. Language Understanding for Text-based Games Using Deep Reinforcement Learning]

• [6. Learning to Communicate to Solve Riddles with Deep Distributed Recurrent Q-Networks]

• [7. Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation]

• [8. Recurrent Reinforcement Learning: A Hybrid Approach]

• [9. Value Iteration Networks, NIPS, 2016]

• [10. MazeBase：A sandbox for learning from games]

• [11. Strategic Attentive Writer for Learning Macro-Actions]

四. 基于策略梯度的深度強化學習

深度策略梯度：

• [1. End-to-End Training of Deep Visuomotor Policies]

• [2. Learning Deep Control Policies for Autonomous Aerial Vehicles with MPC-Guided Policy Search]

• [3. Trust Region Policy Optimization]

深度演員評論家算法：

• [1. Deterministic Policy Gradient Algorithms]

• [2. Continuous control with deep reinforcement learning]

• [3. High-Dimensional Continuous Control Using Using Generalized Advantage Estimation]

• [4. Compatible Value Gradients for Reinforcement Learning of Continuous Deep Policies]

• [5. Deep Reinforcement Learning in Parameterized Action Space]

• [6. Memory-based control with recurrent neural networks]

• [7. Terrain-adaptive locomotion skills using deep reinforcement learning]

• [8. Compatible Value Gradients for Reinforcement Learning of Continuous Deep Policies]

• [9. SAMPLE EFFICIENT ACTOR-CRITIC WITH EXPERIENCE REPLAY]

搜索與監督：

• [1. End-to-End Training of Deep Visuomotor Policies]

• [2. Interactive Control of Diverse Complex Characters with Neural Networks]

連續動作空間下探索改進：

• [1. Curiosity-driven Exploration in DRL via Bayesian Neuarl Networks]

结合策略梯度和Q學習：

• [1. Q-PROP: SAMPLE-EFFICIENT POLICY GRADIENT WITH AN OFF-POLICY CRITIC]

• [2. PGQ: COMBINING POLICY GRADIENT AND Q-LEARNING]

其它策略梯度文章：

• [1. Gradient Estimation Using Stochastic Computation Graphs]

• [2. Continuous Deep Q-Learning with Model-based Acceleration]

• [3. Benchmarking Deep Reinforcement Learning for Continuous Control]

• [4. Learning Continuous Control Policies by Stochastic Value Gradients]

• [5. Generalizing Skills with Semi-Supervised Reinforcement Learning]

五. 分層DRL

• [1. Deep Successor Reinforcement Learning]

• [2. Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation]

• [3. Hierarchical Reinforcement Learning using Spatio-Temporal Abstractions and Deep Neural Networks]

• [4. Stochastic Neural Networks for Hierarchical Reinforcement Learning – Authors: Carlos Florensa, Yan Duan, Pieter Abbeel]

六. DRL中的多任務和遷移學習

• [1. ADAAPT: A Deep Architecture for Adaptive Policy Transfer from Multiple Sources]

• [2. A Deep Hierarchical Approach to Lifelong Learning in Minecraft]

• [3. Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning]

• [4. Policy Distillation]

• [5. Progressive Neural Networks]

• [6. Universal Value Function Approximators]

• [7. Multi-task learning with deep model based reinforcement learning]

• [8. Modular Multitask Reinforcement Learning with Policy Sketches]

七. 基于外部記憶模塊的DRL模型

• [1. Control of Memory, Active Perception, and Action in Minecraft]

• [2. Model-Free Episodic Control]

八. DRL中探索與利用問題

• [1. Action-Conditional Video Prediction using Deep Networks in Atari Games]

• [2. Curiosity-driven Exploration in Deep Reinforcement Learning via Bayesian Neural Networks]

• [3. Deep Exploration via Bootstrapped DQN]

• [4. Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation]

• [5. Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models]

• [6. Unifying Count-Based Exploration and Intrinsic Motivation]

• [7. #Exploration: A Study of Count-Based Exploration for Deep Reinforcemen Learning]

• [8. Surprise-Based Intrinsic Motivation for Deep Reinforcement Learning]

• [9. VIME: Variational Information Maximizing Exploration]

九. 多Agent的DRL

• [1. Learning to Communicate to Solve Riddles with Deep Distributed Recurrent Q-Networks]

• [2. Multiagent Cooperation and Competition with Deep Reinforcement Learning]

十. 逆向DRL

• [1. Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization]

• [2. Maximum Entropy Deep Inverse Reinforcement Learning]

• [3. Generalizing Skills with Semi-Supervised Reinforcement Learning]

十一. 探索+監督學習

• [1. Deep learning for real-time Atari game play using offline Monte-Carlo tree search planning]

• [2. Better Computer Go Player with Neural Network and Long-term Prediction]

• [3. Mastering the game of Go with deep neural networks and tree search, D. Silver et al., Nature, 2016.]

十二. 異步DRL

• [1. Asynchronous Methods for Deep Reinforcement Learning]

• [2. Reinforcement Learning through Asynchronous Advantage Actor-Critic on a GPU]

十三：適用于難度較大的遊戲場景

• [1. Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation, T. D. Kulkarni et al., arXiv, 2016.]

• [2. Strategic Attentive Writer for Learning Macro-Actions]

• [3. Unifying Count-Based Exploration and Intrinsic Motivation]

十四：單個網路玩多個遊戲

• [1. Policy Distillation]

• [2. Universal Value Function Approximators]

• [3. Learning values across many orders of magnitude]

十五：德州poker

• [1. Deep Reinforcement Learning from Self-Play in Imperfect-Information Games]

• [2. Fictitious Self-Play in Extensive-Form Games]

• [3. Smooth UCT search in computer poker]

十六：Doom遊戲

• [1. ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learning]

• [2. Training Agent for First-Person Shooter Game with Actor-Critic Curriculum Learning]

• [3. Playing FPS Games with Deep Reinforcement Learning]

• [4. LEARNING TO ACT BY PREDICTING THE FUTURE]

• [5. Deep Reinforcement Learning From Raw Pixels in Doom]

十七：大规模動作空間

• [1. Deep Reinforcement Learning in Large Discrete Action Spaces]

十八：參數化連續動作空間

• [1. Deep Reinforcement Learning in Parameterized Action Space]

十九：Deep Model

• [1. Learning Visual Predictive Models of Physics for Playing Billiards]

• [2. J. Schmidhuber, On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models, arXiv, 2015. arXiv]

• [3. Learning Continuous Control Policies by Stochastic Value Gradients]

• [4.Data-Efficient Learning of Feedback Policies from Image Pixels using Deep Dynamical Models]

• [5. Action-Conditional Video Prediction using Deep Networks in Atari Games]

• [6. Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models]

二十：DRL應用

機器人領域：

• [1. Trust Region Policy Optimization]

• [2. Towards Vision-Based Deep Reinforcement Learning for Robotic Motion Control]

• [3. Path Integral Guided Policy Search]

• [4. Memory-based control with recurrent neural networks]

• [5. Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collection]

• [6. Learning Deep Neural Network Policies with Continuous Memory States]

• [7. High-Dimensional Continuous Control Using Generalized Advantage Estimation]

• [8. Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization]

• [9. End-to-End Training of Deep Visuomotor Policies]

• [10. DeepMPC: Learning Deep Latent Features for Model Predictive Control]

• [11. Deep Visual Foresight for Planning Robot Motion]

• [12. Deep Reinforcement Learning for Robotic Manipulation]

• [13. Continuous Deep Q-Learning with Model-based Acceleration]

• [14. Collective Robot Reinforcement Learning with Distributed Asynchronous Guided Policy Search]

• [15. Asynchronous Methods for Deep Reinforcement Learning]

• [16. Learning Continuous Control Policies by Stochastic Value Gradients]

機器翻譯:

• [1. Simultaneous Machine Translation using Deep Reinforcement Learning]

目標定位：

• [1. Active Object Localization with Deep Reinforcement Learning]

目標驅動之視覺導航：

• [1. Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning]

自動調控參數：

• [1. Using Deep Q-Learning to Control Optimization Hyperparameters]

人機對話：

• [1. Deep Reinforcement Learning for Dialogue Generation]

• [2. SimpleDS: A Simple Deep Reinforcement Learning Dialogue System]

• [3. Strategic Dialogue Management via Deep Reinforcement Learning]

• [4. Towards End-to-End Learning for Dialog State Tracking and Management using Deep Reinforcement Learning]

視頻檢測：

• [1. Action-Conditional Video Prediction using Deep Networks in Atari Games]

文本至語音：

• [1. WaveNet: A Generative Model for Raw Audio]

文本生成：

• [1. Generating Text with Deep Reinforcement Learning]

文本遊戲：

• [1. Language Understanding for Text-based Games Using Deep Reinforcement Learning]

DRL加收斂：

• [1. Deep Reinforcement Learning for Accelerating the Convergence Rate]

利用DRL來設計神經網路：

• [1. Designing Neural Network Architectures using Reinforcement Learning]

• [2. Tuning Recurrent Neural Networks with Reinforcement Learning]

• [3. Neural Architecture Search with Reinforcement Learning]

控制交通信號：

• [1. Using a Deep Reinforcement Learning Agent for Traffic Signal Control]

自動駕駛：

• [1. CARMA: A Deep Reinforcement Learning Approach to Autonomous Driving]

• [2. Deep Reinforcement Learning for Simulated Autonomous Vehicle Control]

• [3. Deep Reinforcement Learning framework for Autonomous Driving]

二十一：其它方向

避免危險狀態：

• [1. Combating Deep Reinforcement Learning’s Sisyphean Curse with Intrinsic Fear]

DRL中On-Policy vs. Off-Policy 比較：

• [1. On-Policy vs. Off-Policy Updates for Deep Reinforcement Learning]