深度强化学习 DQN系列论文

[{"title":"（ 51 个子文件 69.27MB ） 深度强化学习 DQN系列论文","children":[{"title":"DQN 算法改进","children":[{"title":"Dynamic Frame skip Deep Q Network.pdf <span style='color:#111;'> 588.35KB </span>","children":null,"spread":false},{"title":"Increasing the Action Gap New Operators for Reinforcement Learning.pdf <span style='color:#111;'> 979.22KB </span>","children":null,"spread":false},{"title":"Dueling Network Architectures for Deep Reinforcement Learning.pdf <span style='color:#111;'> 672.37KB </span>","children":null,"spread":false},{"title":"Learning to Play in a Day Faster Deep Reinforcement Learning by Optimality Tightening.pdf <span style='color:#111;'> 1.18MB </span>","children":null,"spread":false},{"title":"Safe and Efficient Off-Policy Reinforcement Learning.pdf <span style='color:#111;'> 556.93KB </span>","children":null,"spread":false},{"title":"Massively Parallel Methods for Deep Reinforcement Learning.pdf <span style='color:#111;'> 2.71MB </span>","children":null,"spread":false},{"title":"Prioritized Experience Replay.pdf <span style='color:#111;'> 1.61MB </span>","children":null,"spread":false},{"title":"Averaged-DQN Variance Reduction and Stabilizationfor Deep Reinforcement Learning.pdf <span style='color:#111;'> 920.65KB </span>","children":null,"spread":false},{"title":"Deep Reinforcement Learning with Double Q-learning.pdf <span style='color:#111;'> 770.57KB </span>","children":null,"spread":false},{"title":"Deep Exploration via Bootstrapped DQN.pdf <span style='color:#111;'> 6.56MB </span>","children":null,"spread":false},{"title":"Learning functions across many orders of magnitudes.pdf <span style='color:#111;'> 803.88KB </span>","children":null,"spread":false},{"title":"The Predictron End-To-End Learning and Planning.pdf <span style='color:#111;'> 1.74MB </span>","children":null,"spread":false},{"title":"How to Discount Deep Reinforcement Learning Towards New Dynamic Strategies.pdf <span style='color:#111;'> 1.02MB </span>","children":null,"spread":false},{"title":"State of the Art Control of Atari Games Using Shallow Reinforcement Learning.pdf <span style='color:#111;'> 802.04KB </span>","children":null,"spread":false}],"spread":false},{"title":"DQN 模型改进","children":[{"title":"Hierarchical Deep Reinforcement Learning Integrating Temporal Abstraction and Intrinsic Motivation.pdf <span style='color:#111;'> 1.31MB </span>","children":null,"spread":false},{"title":"Strategic Attentive Writer for Learning Macro-Actions.pdf <span style='color:#111;'> 718.23KB </span>","children":null,"spread":false},{"title":"Progressive Neural Networks.pdf <span style='color:#111;'> 4.08MB </span>","children":null,"spread":false},{"title":"Language Understanding for Text-based Games Using Deep Reinforcement Learning.pdf <span style='color:#111;'> 597.91KB </span>","children":null,"spread":false},{"title":"Recurrent Reinforcement Learning A Hybrid Approach.pdf <span style='color:#111;'> 430.63KB </span>","children":null,"spread":false},{"title":"Value Iteration Networks.pdf <span style='color:#111;'> 525.18KB </span>","children":null,"spread":false},{"title":"Deep Recurrent Q-Learning for Partially Observable MDPs.pdf <span style='color:#111;'> 823.38KB </span>","children":null,"spread":false},{"title":"MazeBase A Sandbox for Learning from Games.pdf <span style='color:#111;'> 394.73KB </span>","children":null,"spread":false},{"title":"Control of Memory, Active Perception, and Action in Minecraft.pdf <span style='color:#111;'> 7.74MB </span>","children":null,"spread":false},{"title":"Deep Attention Recurrent Q-Network.pdf <span style='color:#111;'> 308.84KB </span>","children":null,"spread":false},{"title":"Learning to Communicate to Solve Riddles with Deep Distributed Recurrent Q-Networks.pdf <span style='color:#111;'> 1000.42KB </span>","children":null,"spread":false}],"spread":false},{"title":"基于策略梯度的深度强化学习","children":[{"title":"Deep Reinforcement Learning in Parameterized Action Space.pdf <span style='color:#111;'> 559.33KB </span>","children":null,"spread":false},{"title":"Efficient Exploration for Dialogue Policy Learning with BBQ Networks & Replay Buffer Spiking.pdf <span style='color:#111;'> 657.07KB </span>","children":null,"spread":false},{"title":"Combining policy gradient and Q-learning.pdf <span style='color:#111;'> 1.19MB </span>","children":null,"spread":false},{"title":"Learning Deep Control Policies for Autonomous Aerial Vehicles with MPC-Guided Policy Search.pdf <span style='color:#111;'> 860.74KB </span>","children":null,"spread":false},{"title":"Sample Efficient Actor-Critic with Experience Replay.pdf <span style='color:#111;'> 1.38MB </span>","children":null,"spread":false},{"title":"Deterministic Policy Gradient Algorithms.pdf <span style='color:#111;'> 335.61KB </span>","children":null,"spread":false},{"title":"End-to-End Training of Deep Visuomotor Policies.pdf <span style='color:#111;'> 4.51MB </span>","children":null,"spread":false},{"title":"Trust Region Policy Optimization.pdf <span style='color:#111;'> 1000.39KB </span>","children":null,"spread":false},{"title":"Continuous control with deep reinforcement learning.pdf <span style='color:#111;'> 648.14KB </span>","children":null,"spread":false},{"title":"Compatible Value Gradients for Reinforcement Learning of Continuous Deep Policies(1).pdf <span style='color:#111;'> 1.04MB </span>","children":null,"spread":false},{"title":"Interactive Control of Diverse Complex Characters with Neural Networks.pdf <span style='color:#111;'> 882.15KB </span>","children":null,"spread":false},{"title":"Memory-based control with recurrent neural networks.pdf <span style='color:#111;'> 677.66KB </span>","children":null,"spread":false},{"title":"Compatible Value Gradients for Reinforcement Learning of Continuous Deep Policies.pdf <span style='color:#111;'> 1.04MB </span>","children":null,"spread":false},{"title":"Q-Prop Sample-Efficient Policy Gradient with An Off-Policy Critic.pdf <span style='color:#111;'> 830.90KB </span>","children":null,"spread":false},{"title":"Learning Continuous Control Policies by Stochastic Value Gradients.pdf <span style='color:#111;'> 834.26KB </span>","children":null,"spread":false},{"title":"Continuous Deep Q-Learning with Model-based Acceleration.pdf <span style='color:#111;'> 1.63MB </span>","children":null,"spread":false},{"title":"Terrain-Adaptive Locomotion Skills Using Deep Reinforcement Learning .pdf <span style='color:#111;'> 8.41MB </span>","children":null,"spread":false},{"title":"Gradient Estimation Using Stochastic Computation Graphs.pdf <span style='color:#111;'> 433.09KB </span>","children":null,"spread":false},{"title":"Benchmarking Deep Reinforcement Learning for Continuous Control.pdf <span style='color:#111;'> 1.17MB </span>","children":null,"spread":false},{"title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation.pdf <span style='color:#111;'> 1.71MB </span>","children":null,"spread":false}],"spread":false},{"title":"分层DRL","children":[{"title":"Stochastic Neural Networks for Hierarchical Reinforcement Learning.pdf <span style='color:#111;'> 3.08MB </span>","children":null,"spread":false},{"title":"Hierarchical Deep Reinforcement Learning Integrating Temporal Abstraction and Intrinsic Motivation.pdf <span style='color:#111;'> 1.31MB </span>","children":null,"spread":false},{"title":"Deep Successor Reinforcement Learning.pdf <span style='color:#111;'> 2.14MB </span>","children":null,"spread":false},{"title":"Hierarchical Reinforcement Learning using Spatio-Temporal Abstractions and Deep Neural Networks.pdf <span style='color:#111;'> 1.15MB </span>","children":null,"spread":false}],"spread":true},{"title":"DQN 开山篇","children":[{"title":"Playing Atari with Deep Reinforcement Learning.pdf <span style='color:#111;'> 425.39KB </span>","children":null,"spread":false},{"title":"Human-level control through deep reinforcementlearning.pdf <span style='color:#111;'> 4.39MB </span>","children":null,"spread":false}],"spread":true}],"spread":true}]