写点什么

深度增强学习方向论文整理

  • 2019-11-29
  • 本文字数:5536 字

    阅读完需:约 18 分钟

深度增强学习方向论文整理

一. 开山鼻祖 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 的各种改进版本(侧重于算法上的改进)

  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(11.13 更新)

  12. Deep Reinforcement Learning with Averaged Target DQN(11.14 更新)

  13. Safe and Efficient Off-Policy Reinforcement Learning(12.20 更新)

  14. The Predictron: End-To-End Learning and Planning (1.3 更新)

三. DQN 的各种改进版本(侧重于模型的改进)

  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 (12.20 更新)

  10. MazeBase:A sandbox for learning from games(12.20 更新)

  11. Strategic Attentive Writer for Learning Macro-Actions(12.20 更新)

四. 基于策略梯度的深度强化学习

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


深度行动者评论家算法:


  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(11.13 更新)


搜索与监督:


  1. End-to-End Training of Deep Visuomotor Policies

  2. Interactive Control of Diverse Complex Characters with Neural Networks


连续动作空间下探索改进:


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


结合策略梯度和 Q 学习:


  1. Q-PROP: SAMPLE-EFFICIENT POLICY GRADIENT WITH AN OFF-POLICY CRITIC(11.13 更新)

  2. PGQ: COMBINING POLICY GRADIENT AND Q-LEARNING(11.13 更新)


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(12.20 更新)

五. 分层 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 (11.14 更新)

六. DRL 中的多任务和迁移学习

  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(11.14 更新)

  8. Modular Multitask Reinforcement Learning with Policy Sketches (11.14 更新)

七. 基于外部记忆模块的 DRL 模型

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

  2. Model-Free Episodic Control

八. DRL 中探索与利用问题

  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(11.14 更新)

  8. Surprise-Based Intrinsic Motivation for Deep Reinforcement Learning(11.14 更新)

  9. VIME: Variational Information Maximizing Exploration(12.20 更新)

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(11.14 更新)

十一. 探索+监督学习

  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. 异步 DRL

  1. Asynchronous Methods for Deep Reinforcement Learning

  2. Reinforcement Learning through Asynchronous Advantage Actor-Critic on a GPU(11.14 更新)

十三:适用于难度较大的游戏场景

  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:单个网络玩多个游戏

  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 游戏

  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(11.13 更新)

  5. Deep Reinforcement Learning From Raw Pixels in Doom(11.14 更新)

十七:大规模动作空间

  1. Deep Reinforcement Learning in Large Discrete Action Spaces

十八:参数化连续动作空间

  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


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

  2. Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models

二十:DRL 应用

机器人领域:


  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


机器翻译:


  1. Simultaneous Machine Translation using Deep Reinforcement Learning


目标定位:


  1. Active Object Localization with Deep Reinforcement Learning


目标驱动的视觉导航:


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


自动调控参数:


  1. Using Deep Q-Learning to Control Optimization Hyperparameters


人机对话:


  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


视频预测:


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


文本到语音:


  1. WaveNet: A Generative Model for Raw Audio


文本生成:


  1. Generating Text with Deep Reinforcement Learning


文本游戏:


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


无线电操控和信号监控:


  1. Deep Reinforcement Learning Radio Control and Signal Detection with KeRLym, a Gym RL Agent


DRL 来学习做物理实验:


  1. LEARNING TO PERFORM PHYSICS EXPERIMENTS VIA DEEP REINFORCEMENT LEARNING(11.13 更新)


DRL 加速收敛:


  1. Deep Reinforcement Learning for Accelerating the Convergence Rate(11.14 更新)


利用 DRL 来设计神经网络:


  1. Designing Neural Network Architectures using Reinforcement Learning(11.14 更新)

  2. Tuning Recurrent Neural Networks with Reinforcement Learning(11.14 更新)

  3. Neural Architecture Search with Reinforcement Learning(11.14 更新)


控制信号灯:


  1. Using a Deep Reinforcement Learning Agent for Traffic Signal Control(11.14 更新)


自动驾驶:


  1. CARMA: A Deep Reinforcement Learning Approach to Autonomous Driving(12.20 更新)

  2. Deep Reinforcement Learning for Simulated Autonomous Vehicle Control(12.20 更新)

  3. Deep Reinforcement Learning framework for Autonomous Driving(12.20 更新)

二十一:其它方向

避免危险状态:


  1. Combating Deep Reinforcement Learning’s Sisyphean Curse with Intrinsic Fear (11.14 更新)


DRL 中 On-Policy vs. Off-Policy 比较:


  1. On-Policy vs. Off-Policy Updates for Deep Reinforcement Learning(11.14 更新)


注 1:小伙伴们如果觉得论文一个个下载太麻烦,可以私信我,我打包发给你。


注 2:欢迎大家及时补充新的或者我疏漏的文献。


本文转载自 Alex-zhai 知乎账号。


原文链接:https://zhuanlan.zhihu.com/p/23600620


2019-11-29 13:463048

评论

发布
暂无评论
发现更多内容

文献解读-《Beta-amylase and phosphatidic acid involved in recalcitrant seed germination of Chinese chestnut》

INSVAST

农业 基因数据分析 生信服务

分享 | 某头部城商行如何提升反欺诈能力

芯盾时代

金融 手机银行 反欺诈

聊聊测试数据的生成方法

老张

软件测试 质量保障 测试数据

Output Thermal for Mac 操作简便的动态多级失真插件

Rose

fcpx音量大小调节插件 CrumplePop Levelmatic

Rose

fcpx音量大小调节插件 CrumplePop Levelmatic

VMware Cloud Foundation 9 发布 - 领先的多云平台

sysin

云计算 vSphere vmware esxi vcf

从工程师视角看 “Multi-Agent as a Service (MAaaS)”

Baihai IDP

AI LLMs 企业号 8 月 PK 榜 Baihai IDP AI Agents

Plugin Alliance Bettermaker Passive Equalizer(Bettermaker无源均衡器)

Rose

华为亮相KubeCon China 2024 ,引领全球智能化新浪潮

新消费日报

Skew for mac 快速倾斜形状sketch工具+Skew使用方法

Rose

sketch工具 Skew插件下载 快速倾斜形状工具插件

人工智能 | 清华大学ChatGLM大模型

测吧(北京)科技有限公司

测试

ps天文景观插件 Astro Panel Pro for Mac v6.0.0苹果版

Rose

ps天文景观插件 Astro Panel Pro Photoshop插件下载安装

深入解析京东商品详情API返回值:从零到一的全面指南

代码忍者

API 测试 API 策略

探索最佳无代码低代码工具:加速 Web 应用开发

NocoBase

低代码 无代码 Web应用开发

A股迎来中报季,合合信息文档解析技术辅助大模型深度解读财报

合合技术团队

金融 PDF 科技

FCPX插件motionVFX mLowers动态下标题

Rose

fcpx插件 fcpx标题模板 motionVFX mLowers 动态下标题

从零开始带你玩转 AI 变现公开课

测吧(北京)科技有限公司

测试

mac游戏:魔兽争霸3冰封王座Warcraft III for mac 版

你的猪会飞吗

魔兽争霸3 冰封王座 Mac游戏下载

中标智能制造!亚信科技+用友网络,助重庆大型制造企业重塑生产管理

亚信AntDB数据库

AntDB

输入一句话,生成一个应用:低代码平台如何借力AI大模型颠覆开发模式

天津汇柏科技有限公司

低代码平台 AI大模型

从零开始带你玩转 AI 变现公开课

测试人

人工智能 软件测试

WiFi7 New era IPQ9574 and IPQ5332 strong combination, driven QCN9274 and QCN6274 chip high-speed interconnection revolution

wifi6-yiyi

WiFi7

Arturia V Collection X for mac(经典合成器和键盘合集) v27.08.2024最新版

Rose

合成器 Arturia V Collection X

After Effects插件:AutoCircularMotion(图层圆周运动工具AE脚本)

Rose

After Effects插件 图层圆周运动工具 AutoCircularMotion

15款中国风大气水墨笔触PS笔刷

Rose

深度增强学习方向论文整理_语言 & 开发_Alex-zhai_InfoQ精选文章