登录    注册      
    
  

News Message

Deep Reinforcement Learning Papers



Deep Reinforcement Learning Papers



A list of recent papersregarding deep reinforcement learning. 
The papers are organized based on manually-defined bookmarks. 
They are sorted by time to see the recent papers first. 
Any suggestions and pull requests are welcome.

Bookmarks

·        AllPapers

·        ValueFunction Approximation

·        PolicyGradient

·        DiscreteControl

·        ContinuousControl

·        TextDomain

·        VisualDomain

·        Robotics

·        Games

·        Monte-CarloTree Search

·        InverseReinforcement Learning

·        ImprovingExploration

·        TransferLearning

·        Multi-Agent

All Papers

·        ContinuousDeep Q-Learning with Model-based Acceleration,Shixiang Gu et al., arXiv, 2016.

·        DeepExploration via Bootstrapped DQN, I.Osband et al., arXiv, 2016.

·        ValueIteration Networks, A. Tamar etal., arXiv, 2016.

·        Learningto Communicate to Solve Riddles with Deep Distributed Recurrent Q-Networks, J. N.Foerster et al., arXiv, 2016.

·        AsynchronousMethods for Deep Reinforcement Learning, V. Mnihet al., arXiv, 2016.

·        Masteringthe game of Go with deep neural networks and tree search, D.Silver et al., Nature, 2016.

·        Increasingthe Action Gap: New Operators for Reinforcement Learning, M. G.Bellemare et al., AAAI, 2016.

·        Memory-basedcontrol with recurrent neural networks, N.Heess et al., NIPS Workshop, 2015.

·        How toDiscount Deep Reinforcement Learning: Towards New Dynamic Strategies, V.François-Lavet et al., NIPS Workshop, 2015.

·        MultiagentCooperation and Competition with Deep Reinforcement Learning, A.Tampuu et al., arXiv, 2015.

·        StrategicDialogue Management via Deep Reinforcement Learning, H.Cuayáhuitl et al., NIPS Workshop, 2015.

·        MazeBase:A Sandbox for Learning from Games, S.Sukhbaatar et al., arXiv, 2016.

·        LearningSimple Algorithms from Examples, W.Zaremba et al., arXiv, 2015.

·        DuelingNetwork Architectures for Deep Reinforcement Learning, Z. Wanget al., arXiv, 2015.

·        Actor-Mimic:Deep Multitask and Transfer Reinforcement Learning, E.Parisotto, et al., ICLR, 2016.

·        BetterComputer Go Player with Neural Network and Long-term Prediction, Y. Tianet al., ICLR, 2016.

·        PolicyDistillation, A. A. Rusu etat., ICLR, 2016.

·        PrioritizedExperience Replay, T. Schaul etal., ICLR, 2016.

·        DeepReinforcement Learning with an Action Space Defined by Natural Language, J. Heet al., arXiv, 2015.

·        DeepReinforcement Learning in Parameterized Action Space, M.Hausknecht et al., ICLR, 2016.

·        TowardsVision-Based Deep Reinforcement Learning for Robotic Motion Control, F.Zhang et al., arXiv, 2015.

·        GeneratingText with Deep Reinforcement Learning, H.Guo, arXiv, 2015.

·        ADAAPT:A Deep Architecture for Adaptive Policy Transfer from Multiple Sources, J.Rajendran et al., arXiv, 2015.

·        VariationalInformation Maximisation for Intrinsically Motivated Reinforcement Learning, S.Mohamed and D. J. Rezende,arXiv, 2015.

·        DeepReinforcement Learning with Double Q-learning, H. vanHasselt et al., arXiv, 2015.

·        RecurrentReinforcement Learning: A Hybrid Approach, X. Liet al., arXiv, 2015.

·        Continuouscontrol with deep reinforcement learning, T. P.Lillicrap et al., ICLR, 2016.

·        LanguageUnderstanding for Text-based Games Using Deep Reinforcement Learning, K.Narasimhan et al., EMNLP, 2015.

·        Giraffe:Using Deep Reinforcement Learning to Play Chess, M.Lai, arXiv, 2015.

·        Action-ConditionalVideo Prediction using Deep Networks in Atari Games, J. Ohet al., NIPS, 2015.

·        LearningContinuous Control Policies by Stochastic Value Gradients, N.Heess et al., NIPS, 2015.

·        LearningDeep Neural Network Policies with Continuous Memory States, M.Zhang et al., arXiv, 2015.

·        DeepRecurrent Q-Learning for Partially Observable MDPs, M.Hausknecht and P. Stone, arXiv, 2015.

·        Listen,Attend, and Walk: Neural Mapping of Navigational Instructions to ActionSequences, H. Mei et al., arXiv, 2015.

·        IncentivizingExploration In Reinforcement Learning With Deep Predictive Models, B. C.Stadie et al., arXiv, 2015.

·        MaximumEntropy Deep Inverse Reinforcement Learning, M.Wulfmeier et al., arXiv, 2015.

·        High-DimensionalContinuous Control Using Generalized Advantage Estimation, J.Schulman et al., ICLR, 2016.

·        End-to-EndTraining of Deep Visuomotor Policies, S.Levine et al., arXiv, 2015.

·        DeepMPC:Learning Deep Latent Features for Model Predictive Control, I.Lenz, et al., RSS, 2015.

·        UniversalValue Function Approximators, T. Schaulet al., ICML, 2015.

·        DeterministicPolicy Gradient Algorithms, D. Silver etal., ICML, 2015.

·        MassivelyParallel Methods for Deep Reinforcement Learning, A. Nairet al., ICML Workshop, 2015.

·        TrustRegion Policy Optimization, J. Schulman etal., ICML, 2015.

·        Human-levelcontrol through deep reinforcement learning, V. Mnihet al., Nature, 2015.

·        DeepLearning for Real-Time Atari Game Play Using Offline Monte-Carlo Tree SearchPlanning, X. Guo et al., NIPS, 2014.

·        PlayingAtari with Deep Reinforcement Learning, V. Mnihet al., NIPS Workshop, 2013.

Value FunctionApproximation

·        ContinuousDeep Q-Learning with Model-based Acceleration,Shixiang Gu et al., arXiv, 2016.

·        DeepExploration via Bootstrapped DQN, I.Osband et al., arXiv, 2016.

·        ValueIteration Networks, A. Tamar etal., arXiv, 2016.

·        Learningto Communicate to Solve Riddles with Deep Distributed Recurrent Q-Networks, J. N.Foerster et al., arXiv, 2016.

·        AsynchronousMethods for Deep Reinforcement Learning, V. Mnihet al., arXiv, 2016.

·        Masteringthe game of Go with deep neural networks and tree search, D.Silver et al., Nature, 2016.

·        Increasingthe Action Gap: New Operators for Reinforcement Learning, M. G.Bellemare et al., AAAI, 2016.

·        How toDiscount Deep Reinforcement Learning: Towards New Dynamic Strategies, V.François-Lavet et al., NIPS Workshop, 2015.

·        MultiagentCooperation and Competition with Deep Reinforcement Learning, A.Tampuu et al., arXiv, 2015.

·        StrategicDialogue Management via Deep Reinforcement Learning, H.Cuayáhuitl et al., NIPS Workshop, 2015.

·        LearningSimple Algorithms from Examples, W.Zaremba et al., arXiv, 2015.

·        DuelingNetwork Architectures for Deep Reinforcement Learning, Z. Wanget al., arXiv, 2015.

·        PrioritizedExperience Replay, T. Schaul etal., ICLR, 2016.

·        DeepReinforcement Learning with an Action Space Defined by Natural Language, J. Heet al., arXiv, 2015.

·        DeepReinforcement Learning in Parameterized Action Space, M.Hausknecht et al., ICLR, 2016.

·        TowardsVision-Based Deep Reinforcement Learning for Robotic Motion Control, F.Zhang et al., arXiv, 2015.

·        GeneratingText with Deep Reinforcement Learning, H.Guo, arXiv, 2015.

·        DeepReinforcement Learning with Double Q-learning, H. vanHasselt et al., arXiv, 2015.

·        RecurrentReinforcement Learning: A Hybrid Approach, X. Liet al., arXiv, 2015.

·        Continuouscontrol with deep reinforcement learning, T. P.Lillicrap et al., ICLR, 2016.

·        LanguageUnderstanding for Text-based Games Using Deep Reinforcement Learning, K.Narasimhan et al., EMNLP, 2015.

·        Action-ConditionalVideo Prediction using Deep Networks in Atari Games, J. Ohet al., NIPS, 2015.

·        DeepRecurrent Q-Learning for Partially Observable MDPs, M.Hausknecht and P. Stone, arXiv, 2015.

·        IncentivizingExploration In Reinforcement Learning With Deep Predictive Models, B. C.Stadie et al., arXiv, 2015.

·        MassivelyParallel Methods for Deep Reinforcement Learning, A. Nairet al., ICML Workshop, 2015.

·        Human-levelcontrol through deep reinforcement learning, V. Mnihet al., Nature, 2015.

·        PlayingAtari with Deep Reinforcement Learning, V. Mnihet al., NIPS Workshop, 2013.

Policy Gradient

·        AsynchronousMethods for Deep Reinforcement Learning, V. Mnihet al., arXiv, 2016.

·        Masteringthe game of Go with deep neural networks and tree search, D.Silver et al., Nature, 2016.

·        Memory-basedcontrol with recurrent neural networks, N.Heess et al., NIPS Workshop, 2015.

·        MazeBase:A Sandbox for Learning from Games, S.Sukhbaatar et al., arXiv, 2016.

·        ADAAPT:A Deep Architecture for Adaptive Policy Transfer from Multiple Sources, J.Rajendran et al., arXiv, 2015.

·        Continuouscontrol with deep reinforcement learning, T. P.Lillicrap et al., ICLR, 2016.

·        LearningContinuous Control Policies by Stochastic Value Gradients, N.Heess et al., NIPS, 2015.

·        High-DimensionalContinuous Control Using Generalized Advantage Estimation, J.Schulman et al., ICLR, 2016.

·        End-to-EndTraining of Deep Visuomotor Policies, S.Levine et al., arXiv, 2015.

·        DeterministicPolicy Gradient Algorithms, D. Silver etal., ICML, 2015.

·        TrustRegion Policy Optimization, J. Schulman etal., ICML, 2015.

Discrete Control

·        DeepExploration via Bootstrapped DQN, I.Osband et al., arXiv, 2016.

·        ValueIteration Networks, A. Tamar etal., arXiv, 2016.

·        Learningto Communicate to Solve Riddles with Deep Distributed Recurrent Q-Networks, J. N.Foerster et al., arXiv, 2016.

·        AsynchronousMethods for Deep Reinforcement Learning, V. Mnihet al., arXiv, 2016.

·        Masteringthe game of Go with deep neural networks and tree search, D.Silver et al., Nature, 2016.

·        Increasingthe Action Gap: New Operators for Reinforcement Learning, M. G.Bellemare et al., AAAI, 2016.

·        How toDiscount Deep Reinforcement Learning: Towards New Dynamic Strategies, V.François-Lavet et al., NIPS Workshop, 2015.

·        MultiagentCooperation and Competition with Deep Reinforcement Learning, A.Tampuu et al., arXiv, 2015.

·        StrategicDialogue Management via Deep Reinforcement Learning, H.Cuayáhuitl et al., NIPS Workshop, 2015.

·        LearningSimple Algorithms from Examples, W.Zaremba et al., arXiv, 2015.

·        DuelingNetwork Architectures for Deep Reinforcement Learning, Z. Wanget al., arXiv, 2015.

·        BetterComputer Go Player with Neural Network and Long-term Prediction, Y. Tianet al., ICLR, 2016.

·        Actor-Mimic:Deep Multitask and Transfer Reinforcement Learning, E.Parisotto, et al., ICLR, 2016.

·        PolicyDistillation, A. A. Rusu etat., ICLR, 2016.

·        PrioritizedExperience Replay, T. Schaul etal., ICLR, 2016.

·        DeepReinforcement Learning with an Action Space Defined by Natural Language, J. Heet al., arXiv, 2015.

·        DeepReinforcement Learning in Parameterized Action Space, M.Hausknecht et al., ICLR, 2016.

·        TowardsVision-Based Deep Reinforcement Learning for Robotic Motion Control, F.Zhang et al., arXiv, 2015.

·        GeneratingText with Deep Reinforcement Learning, H.Guo, arXiv, 2015.

·        ADAAPT:A Deep Architecture for Adaptive Policy Transfer from Multiple Sources, J.Rajendran et al., arXiv, 2015.

·        VariationalInformation Maximisation for Intrinsically Motivated Reinforcement Learning, S.Mohamed and D. J. Rezende,arXiv, 2015.

·        DeepReinforcement Learning with Double Q-learning, H. vanHasselt et al., arXiv, 2015.

·        RecurrentReinforcement Learning: A Hybrid Approach, X. Liet al., arXiv, 2015.

·        LanguageUnderstanding for Text-based Games Using Deep Reinforcement Learning, K.Narasimhan et al., EMNLP, 2015.

·        Giraffe:Using Deep Reinforcement Learning to Play Chess, M.Lai, arXiv, 2015.

·        Action-ConditionalVideo Prediction using Deep Networks in Atari Games, J. Ohet al., NIPS, 2015.

·        DeepRecurrent Q-Learning for Partially Observable MDPs, M.Hausknecht and P. Stone, arXiv, 2015.

·        Listen,Attend, and Walk: Neural Mapping of Navigational Instructions to ActionSequences, H. Mei et al., arXiv, 2015.

·        IncentivizingExploration In Reinforcement Learning With Deep Predictive Models, B. C.Stadie et al., arXiv, 2015.

·        UniversalValue Function Approximators, T.Schaul et al., ICML, 2015.

·        MassivelyParallel Methods for Deep Reinforcement Learning, A. Nairet al., ICML Workshop, 2015.

·        Human-levelcontrol through deep reinforcement learning, V. Mnihet al., Nature, 2015.

·        DeepLearning for Real-Time Atari Game Play Using Offline Monte-Carlo Tree SearchPlanning, X. Guo et al., NIPS, 2014.

·        PlayingAtari with Deep Reinforcement Learning, V. Mnihet al., NIPS Workshop, 2013.

Continuous Control

·        ContinuousDeep Q-Learning with Model-based Acceleration,Shixiang Gu et al., arXiv, 2016.

·        AsynchronousMethods for Deep Reinforcement Learning, V. Mnihet al., arXiv, 2016.

·        Memory-basedcontrol with recurrent neural networks, N.Heess et al., NIPS Workshop, 2015.

·        VariationalInformation Maximisation for Intrinsically Motivated Reinforcement Learning, S.Mohamed and D. J. Rezende,arXiv, 2015.

·        Continuouscontrol with deep reinforcement learning, T. P.Lillicrap et al., ICLR, 2016.

·        LearningContinuous Control Policies by Stochastic Value Gradients, N.Heess et al., NIPS, 2015.

·        LearningDeep Neural Network Policies with Continuous Memory States, M.Zhang et al., arXiv, 2015.

·        High-DimensionalContinuous Control Using Generalized Advantage Estimation, J.Schulman et al., ICLR, 2016.

·        End-to-EndTraining of Deep Visuomotor Policies, S.Levine et al., arXiv, 2015.

·        DeepMPC:Learning Deep Latent Features for Model Predictive Control, I.Lenz, et al., RSS, 2015.

·        DeterministicPolicy Gradient Algorithms, D. Silver etal., ICML, 2015.

·        TrustRegion Policy Optimization, J. Schulman etal., ICML, 2015.

Text Domain

·        StrategicDialogue Management via Deep Reinforcement Learning, H.Cuayáhuitl et al., NIPS Workshop, 2015.

·        MazeBase:A Sandbox for Learning from Games, S.Sukhbaatar et al., arXiv, 2016.

·        DeepReinforcement Learning with an Action Space Defined by Natural Language, J. Heet al., arXiv, 2015.

·        GeneratingText with Deep Reinforcement Learning, H.Guo, arXiv, 2015.

·        LanguageUnderstanding for Text-based Games Using Deep Reinforcement Learning, K.Narasimhan et al., EMNLP, 2015.

·        Listen,Attend, and Walk: Neural Mapping of Navigational Instructions to ActionSequences, H. Mei et al., arXiv, 2015.

Visual Domain

·        DeepExploration via Bootstrapped DQN, I.Osband et al., arXiv, 2016.

·        ValueIteration Networks, A. Tamar etal., arXiv, 2016.

·        AsynchronousMethods for Deep Reinforcement Learning, V. Mnihet al., arXiv, 2016.

·        Masteringthe game of Go with deep neural networks and tree search, D.Silver et al., Nature, 2016.

·        Increasingthe Action Gap: New Operators for Reinforcement Learning, M. G.Bellemare et al., AAAI, 2016.

·        Memory-basedcontrol with recurrent neural networks, N.Heess et al., NIPS Workshop, 2015.

·        How toDiscount Deep Reinforcement Learning: Towards New Dynamic Strategies, V.François-Lavet et al., NIPS Workshop, 2015.

·        MultiagentCooperation and Competition with Deep Reinforcement Learning, A. Tampuuet al., arXiv, 2015.

·        DuelingNetwork Architectures for Deep Reinforcement Learning, Z. Wanget al., arXiv, 2015.

·        Actor-Mimic:Deep Multitask and Transfer Reinforcement Learning, E.Parisotto, et al., ICLR, 2016.

·        BetterComputer Go Player with Neural Network and Long-term Prediction, Y. Tianet al., ICLR, 2016.

·        PolicyDistillation, A. A. Rusu etat., ICLR, 2016.

·        PrioritizedExperience Replay, T. Schaul etal., ICLR, 2016.

·        DeepReinforcement Learning in Parameterized Action Space, M. Hausknechtet al., ICLR, 2016.

·        TowardsVision-Based Deep Reinforcement Learning for Robotic Motion Control, F.Zhang et al., arXiv, 2015.

·        VariationalInformation Maximisation for Intrinsically Motivated Reinforcement Learning, S.Mohamed and D. J. Rezende,arXiv, 2015.

·        DeepReinforcement Learning with Double Q-learning, H. vanHasselt et al., arXiv, 2015.

·        Continuouscontrol with deep reinforcement learning, T. P.Lillicrap et al., ICLR, 2016.

·        Giraffe:Using Deep Reinforcement Learning to Play Chess, M.Lai, arXiv, 2015.

·        Action-ConditionalVideo Prediction using Deep Networks in Atari Games, J. Ohet al., NIPS, 2015.

·        LearningContinuous Control Policies by Stochastic Value Gradients, N.Heess et al., NIPS, 2015.

·        DeepRecurrent Q-Learning for Partially Observable MDPs, M.Hausknecht and P. Stone, arXiv, 2015.

·        IncentivizingExploration In Reinforcement Learning With Deep Predictive Models, B. C.Stadie et al., arXiv, 2015.

·        High-DimensionalContinuous Control Using Generalized Advantage Estimation, J.Schulman et al., ICLR, 2016.

·        End-to-EndTraining of Deep Visuomotor Policies, S.Levine et al., arXiv, 2015.

·        UniversalValue Function Approximators, T.Schaul et al., ICML, 2015.

·        MassivelyParallel Methods for Deep Reinforcement Learning, A. Nairet al., ICML Workshop, 2015.

·        TrustRegion Policy Optimization, J. Schulman etal., ICML, 2015.

·        Human-levelcontrol through deep reinforcement learning, V. Mnihet al., Nature, 2015.

·        DeepLearning for Real-Time Atari Game Play Using Offline Monte-Carlo Tree SearchPlanning, X. Guo et al., NIPS, 2014.

·        PlayingAtari with Deep Reinforcement Learning, V. Mnihet al., NIPS Workshop, 2013.

Robotics

·        ContinuousDeep Q-Learning with Model-based Acceleration,Shixiang Gu et al., arXiv, 2016.

·        AsynchronousMethods for Deep Reinforcement Learning, V. Mnihet al., arXiv, 2016.

·        Memory-basedcontrol with recurrent neural networks, N.Heess et al., NIPS Workshop, 2015.

·        TowardsVision-Based Deep Reinforcement Learning for Robotic Motion Control, F.Zhang et al., arXiv, 2015.

·        LearningContinuous Control Policies by Stochastic Value Gradients, N. Heesset al., NIPS, 2015.

·        LearningDeep Neural Network Policies with Continuous Memory States, M.Zhang et al., arXiv, 2015.

·        High-DimensionalContinuous Control Using Generalized Advantage Estimation, J.Schulman et al., ICLR, 2016.

·        End-to-EndTraining of Deep Visuomotor Policies, S.Levine et al., arXiv, 2015.

·        DeepMPC:Learning Deep Latent Features for Model Predictive Control, I.Lenz, et al., RSS, 2015.

·        TrustRegion Policy Optimization, J. Schulman etal., ICML, 2015.

Games

·        DeepExploration via Bootstrapped DQN, I.Osband et al., arXiv, 2016.

·        Learningto Communicate to Solve Riddles with Deep Distributed Recurrent Q-Networks, J. N.Foerster et al., arXiv, 2016.

·        AsynchronousMethods for Deep Reinforcement Learning, V. Mnihet al., arXiv, 2016.

·        Masteringthe game of Go with deep neural networks and tree search, D.Silver et al., Nature, 2016.

·        Increasingthe Action Gap: New Operators for Reinforcement Learning, M. G.Bellemare et al., AAAI, 2016.

·        How toDiscount Deep Reinforcement Learning: Towards New Dynamic Strategies, V.François-Lavet et al., NIPS Workshop, 2015.

·        MultiagentCooperation and Competition with Deep Reinforcement Learning, A.Tampuu et al., arXiv, 2015.

·        MazeBase:A Sandbox for Learning from Games, S.Sukhbaatar et al., arXiv, 2016.

·        DuelingNetwork Architectures for Deep Reinforcement Learning, Z. Wanget al., arXiv, 2015.

·        BetterComputer Go Player with Neural Network and Long-term Prediction, Y. Tianet al., ICLR, 2016.

·        Actor-Mimic:Deep Multitask and Transfer Reinforcement Learning, E.Parisotto, et al., ICLR, 2016.

·        PolicyDistillation, A. A. Rusu etat., ICLR, 2016.

·        PrioritizedExperience Replay, T. Schaul etal., ICLR, 2016.

·        DeepReinforcement Learning with an Action Space Defined by Natural Language, J. Heet al., arXiv, 2015.

·        DeepReinforcement Learning in Parameterized Action Space, M.Hausknecht et al., ICLR, 2016.

·        VariationalInformation Maximisation for Intrinsically Motivated Reinforcement Learning, S.Mohamed and D. J. Rezende,arXiv, 2015.

·        DeepReinforcement Learning with Double Q-learning, H. vanHasselt et al., arXiv, 2015.

·        Continuouscontrol with deep reinforcement learning, T. P.Lillicrap et al., ICLR, 2016.

·        LanguageUnderstanding for Text-based Games Using Deep Reinforcement Learning, K. Narasimhanet al., EMNLP, 2015.

·        Giraffe:Using Deep Reinforcement Learning to Play Chess, M.Lai, arXiv, 2015.

·        Action-ConditionalVideo Prediction using Deep Networks in Atari Games, J. Ohet al., NIPS, 2015.

·        DeepRecurrent Q-Learning for Partially Observable MDPs, M.Hausknecht and P. Stone, arXiv, 2015.

·        IncentivizingExploration In Reinforcement Learning With Deep Predictive Models, B. C.Stadie et al., arXiv, 2015.

·        UniversalValue Function Approximators, T.Schaul et al., ICML, 2015.

·        MassivelyParallel Methods for Deep Reinforcement Learning, A. Nairet al., ICML Workshop, 2015.

·        TrustRegion Policy Optimization, J. Schulman etal., ICML, 2015.

·        Human-levelcontrol through deep reinforcement learning, V. Mnihet al., Nature, 2015.

·        DeepLearning for Real-Time Atari Game Play Using Offline Monte-Carlo Tree SearchPlanning, X. Guo et al., NIPS, 2014.

·        PlayingAtari with Deep Reinforcement Learning, V. Mnihet al., NIPS Workshop, 2013.

Monte-Carlo Tree Search

·        Masteringthe game of Go with deep neural networks and tree search, D.Silver et al., Nature, 2016.

·        BetterComputer Go Player with Neural Network and Long-term Prediction, Y. Tianet al., ICLR, 2016.

·        DeepLearning for Real-Time Atari Game Play Using Offline Monte-Carlo Tree SearchPlanning, X. Guo et al., NIPS, 2014.

Inverse ReinforcementLearning

·        MaximumEntropy Deep Inverse Reinforcement Learning, M.Wulfmeier et al., arXiv, 2015.

Transfer Learning

·        Actor-Mimic:Deep Multitask and Transfer Reinforcement Learning, E.Parisotto, et al., ICLR, 2016.

·        PolicyDistillation, A. A. Rusu etat., ICLR, 2016.

·        ADAAPT:A Deep Architecture for Adaptive Policy Transfer from Multiple Sources, J.Rajendran et al., arXiv, 2015.

·        UniversalValue Function Approximators, T.Schaul et al., ICML, 2015.

Improving Exploration

·        DeepExploration via Bootstrapped DQN, I.Osband et al., arXiv, 2016.

·        Action-ConditionalVideo Prediction using Deep Networks in Atari Games, J. Ohet al., NIPS, 2015.

·        IncentivizingExploration In Reinforcement Learning With Deep Predictive Models, B. C.Stadie et al., arXiv, 2015.

Multi-Agent

·        Learningto Communicate to Solve Riddles with Deep Distributed Recurrent Q-Networks, J. N.Foerster et al., arXiv, 2016.

·        MultiagentCooperation and Competition with Deep Reinforcement Learning, A.Tampuu et al., arXiv, 2015.

 




Share Http URL:  http://www.wittx.cn/get_news_message.do?new_id=173



请输入评论





























Best Last Month