【文件属性】：
文件名称：深度强化学习 DQN系列论文
文件大小：69.27MB
文件格式：RAR
更新时间：2023-02-20 09:59:49
深度强化学习 DQN
深度强化学习系列论文，包括最基础的DQN，DQN模型改进，DQN算法改进，分层DRL，基于策略梯度的深度强化学习等等，论文基本源自顶会
【文件预览】：
DQN 算法改进
----Dynamic Frame skip Deep Q Network.pdf(588KB)
----Increasing the Action Gap New Operators for Reinforcement Learning.pdf(979KB)
----Dueling Network Architectures for Deep Reinforcement Learning.pdf(672KB)
----Learning to Play in a Day Faster Deep Reinforcement Learning by Optimality Tightening.pdf(1.18MB)
----Safe and Efficient Off-Policy Reinforcement Learning.pdf(557KB)
----Massively Parallel Methods for Deep Reinforcement Learning.pdf(2.71MB)
----Prioritized Experience Replay.pdf(1.61MB)
----Averaged-DQN Variance Reduction and Stabilizationfor Deep Reinforcement Learning.pdf(921KB)
----Deep Reinforcement Learning with Double Q-learning.pdf(771KB)
----Deep Exploration via Bootstrapped DQN.pdf(6.56MB)
----Learning functions across many orders of magnitudes.pdf(804KB)
----The Predictron End-To-End Learning and Planning.pdf(1.74MB)
----How to Discount Deep Reinforcement Learning Towards New Dynamic Strategies.pdf(1.02MB)
----State of the Art Control of Atari Games Using Shallow Reinforcement Learning.pdf(802KB)
DQN 模型改进
----Hierarchical Deep Reinforcement Learning Integrating Temporal Abstraction and Intrinsic Motivation.pdf(1.31MB)
----Strategic Attentive Writer for Learning Macro-Actions.pdf(718KB)
----Progressive Neural Networks.pdf(4.08MB)
----Language Understanding for Text-based Games Using Deep Reinforcement Learning.pdf(598KB)
----Recurrent Reinforcement Learning A Hybrid Approach.pdf(431KB)
----Value Iteration Networks.pdf(525KB)
----Deep Recurrent Q-Learning for Partially Observable MDPs.pdf(823KB)
----MazeBase A Sandbox for Learning from Games.pdf(395KB)
----Control of Memory, Active Perception, and Action in Minecraft.pdf(7.74MB)
----Deep Attention Recurrent Q-Network.pdf(309KB)
----Learning to Communicate to Solve Riddles with Deep Distributed Recurrent Q-Networks.pdf(1000KB)
基于策略梯度的深度强化学习
----Deep Reinforcement Learning in Parameterized Action Space.pdf(559KB)
----Efficient Exploration for Dialogue Policy Learning with BBQ Networks & Replay Buffer Spiking.pdf(657KB)
----Combining policy gradient and Q-learning.pdf(1.19MB)
----Learning Deep Control Policies for Autonomous Aerial Vehicles with MPC-Guided Policy Search.pdf(861KB)
----Sample Efficient Actor-Critic with Experience Replay.pdf(1.38MB)
----Deterministic Policy Gradient Algorithms.pdf(336KB)
----End-to-End Training of Deep Visuomotor Policies.pdf(4.51MB)
----Trust Region Policy Optimization.pdf(1000KB)
----Continuous control with deep reinforcement learning.pdf(648KB)
----Compatible Value Gradients for Reinforcement Learning of Continuous Deep Policies(1).pdf(1.04MB)
----Interactive Control of Diverse Complex Characters with Neural Networks.pdf(882KB)
----Memory-based control with recurrent neural networks.pdf(678KB)
----Compatible Value Gradients for Reinforcement Learning of Continuous Deep Policies.pdf(1.04MB)
----Q-Prop Sample-Efficient Policy Gradient with An Off-Policy Critic.pdf(831KB)
----Learning Continuous Control Policies by Stochastic Value Gradients.pdf(834KB)
----Continuous Deep Q-Learning with Model-based Acceleration.pdf(1.63MB)
----Terrain-Adaptive Locomotion Skills Using Deep Reinforcement Learning .pdf(8.41MB)
----Gradient Estimation Using Stochastic Computation Graphs.pdf(433KB)
----Benchmarking Deep Reinforcement Learning for Continuous Control.pdf(1.17MB)
----High-Dimensional Continuous Control Using Generalized Advantage Estimation.pdf(1.71MB)
分层DRL
----Stochastic Neural Networks for Hierarchical Reinforcement Learning.pdf(3.08MB)
----Hierarchical Deep Reinforcement Learning Integrating Temporal Abstraction and Intrinsic Motivation.pdf(1.31MB)
----Deep Successor Reinforcement Learning.pdf(2.14MB)
----Hierarchical Reinforcement Learning using Spatio-Temporal Abstractions and Deep Neural Networks.pdf(1.15MB)
DQN 开山篇
----Playing Atari with Deep Reinforcement Learning.pdf(425KB)
----Human-level control through deep reinforcementlearning.pdf(4.39MB)