Deep Reinforcement Learning — Papers (2)

Deep Reinforcement Learning — Papers

Many recent advancements in AI research stem from breakthroughs in deep reinforcement learning. This is a complex and varied field, but Junhyuk
Oh at the University of Michigan has compiled a great list of papers. The list, which originally appeared on GitHub,
are sorted by time with most recent appearing first.

Bookmarks

All Papers

Q-learning

Policy Gradient

Discrete Control

Continuous Control

Text Domain

Visual Domain

Robotics

Games

Monte-Carlo Tree Search

Inverse Reinforcement Learning

Improving Exploration

Transfer Learning

All Papers

Deep Reinforcement Learning with an Unbounded Action Space, J. He et al.,arXiv,
2015.

Deep Reinforcement Learning in Parameterized Action Space, M. Hausknecht et al., arXiv,
2015.

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

Generating Text 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.

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

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

Recurrent Reinforcement Learning: A Hybrid Approach, X. Li et al., arXiv, 2015.

Continuous control with deep reinforcement learning, T. P. Lillicrap et al.,arXiv,
2015.

Language Understanding 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-Conditional Video Prediction using Deep Networks in Atari Games, J. Oh et al., NIPS,
2015.

Learning Deep Neural Network Policies with Continuous Memory States, M. Zhang et al., arXiv,
2015.

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

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

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

Maximum Entropy Deep Inverse Reinforcement Learning, M. Wulfmeier et al.,arXiv,
2015.

End-to-End Training 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.

Universal Value Function Approximators, T. Schaul et al., ICML,
2015.

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

Trust Region Policy Optimization, J. Schulman et al., ICML,
2015.

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

Deep Learning for Real-Time Atari Game
Play Using Offline Monte-Carlo Tree Search Planning, X. Guo et al., NIPS, 2014.

Playing Atari with Deep Reinforcement Learning, V. Mnih et al., NIPS
Workshop, 2013.

Q-learning

Deep Reinforcement Learning with an Unbounded Action Space, J. He et al.,arXiv,
2015.

Deep Reinforcement Learning in Parameterized Action Space, M. Hausknecht et al., arXiv,
2015.

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

Generating Text with Deep Reinforcement Learning, H. Guo, arXiv, 2015.

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

Recurrent Reinforcement Learning: A Hybrid Approach, X. Li et al., arXiv, 2015.

Continuous control with deep reinforcement learning, T. P. Lillicrap et al.,arXiv,
2015.

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

Action-Conditiona
143c7
l Video Prediction using Deep Networks in Atari Games, J. Oh et al., NIPS,
2015.

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

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

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

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

Playing Atari with Deep Reinforcement Learning, V. Mnih et al., NIPS
Workshop, 2013.

Policy Gradient

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

Continuous control with deep reinforcement learning, T. P. Lillicrap et al.,arXiv,
2015.

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

Trust Region Policy Optimization, J. Schulman et al., ICML,
2015.

Discrete Control

Deep Reinforcement Learning with an Unbounded Action Space, J. He et al.,arXiv,
2015.

Deep Reinforcement Learning in Parameterized Action Space, M. Hausknecht et al., arXiv,
2015.

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

Generating Text 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.

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

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

Recurrent Reinforcement Learning: A Hybrid Approach, X. Li et al., arXiv, 2015.

Language Understanding 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-Conditional Video Prediction using Deep Networks in Atari Games, J. Oh et al., NIPS,
2015.

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

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

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

Universal Value Function Approximators, T. Schaul et al., ICML,
2015.

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

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

Deep Learning for Real-Time Atari Game
Play Using Offline Monte-Carlo Tree Search Planning, X. Guo et al., NIPS, 2014.

Playing Atari with Deep Reinforcement Learning, V. Mnih et al., NIPS
Workshop, 2013.

Continuous Control

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

Continuous control with deep reinforcement learning, T. P. Lillicrap et al.,arXiv,
2015.

Learning Deep Neural Network Policies with Continuous Memory States, M. Zhang et al., arXiv,
2015.

End-to-End Training 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.

Trust Region Policy Optimization, J. Schulman et al., ICML,
2015.

Text Domain

Deep Reinforcement Learning with an Unbounded Action Space, J. He et al.,arXiv,
2015.

Generating Text with Deep Reinforcement Learning, H. Guo, arXiv, 2015.

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

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

Visual Domain

Deep Reinforcement Learning in Parameterized Action Space, M. Hausknecht et al., arXiv,
2015.

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

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

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

Continuous control with deep reinforcement learning, T. P. Lillicrap et al.,arXiv,
2015.

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

Action-Conditional Video Prediction using Deep Networks in Atari Games, J. Oh et al., NIPS,
2015.

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

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

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

Universal Value Function Approximators, T. Schaul et al., ICML,
2015.

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

Trust Region Policy Optimization, J. Schulman et al., ICML,
2015.

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

Deep Learning for Real-Time Atari Game
Play Using Offline Monte-Carlo Tree Search Planning, X. Guo et al., NIPS, 2014.

Playing Atari with Deep Reinforcement Learning, V. Mnih et al., NIPS
Workshop, 2013.

Robotics

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

Learning Deep Neural Network Policies with Continuous Memory States, M. Zhang et al., arXiv,
2015.

End-to-End Training 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.

Trust Region Policy Optimization, J. Schulman et al., ICML,
2015.

Games

Deep Reinforcement Learning with an Unbounded Action Space, J. He et al.,arXiv,
2015.

Deep Reinforcement Learning in Parameterized Action Space, M. Hausknecht et al., arXiv,
2015.

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

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

Continuous control with deep reinforcement learning, T. P. Lillicrap et al.,arXiv,
2015.

Language Understanding 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-Conditional Video Prediction using Deep Networks in Atari Games, J. Oh et al., NIPS,
2015.

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

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

Universal Value Function Approximators, T. Schaul et al., ICML,
2015.

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

Trust Region Policy Optimization, J. Schulman et al., ICML,
2015.

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

Deep Learning for Real-Time Atari Game
Play Using Offline Monte-Carlo Tree Search Planning, X. Guo et al., NIPS, 2014.

Playing Atari with Deep Reinforcement Learning, V. Mnih et al., NIPS
Workshop, 2013.

Monte-Carlo Tree Search

Deep Learning for Real-Time Atari Game
Play Using Offline Monte-Carlo Tree Search Planning, X. Guo et al., NIPS, 2014.

Inverse Reinforcement Learning

Maximum Entropy Deep Inverse Reinforcement Learning, M. Wulfmeier et al.,arXiv,
2015.

Transfer Learning

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

Improving Exploration

Action-Conditional Video Prediction using Deep Networks in Atari Games, J. Oh et al., NIPS,
2015.

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

Josh.ai is an artificial intelligence agent for your home. If you’re interested in learning more, visit us at https://josh.ai.