Deep Reinforcement Learning Workshop, NIPS 2016
The third Deep Reinforcement Learning Workshop will be held at NIPS 2016 in Barcelona, Spain on Friday December 9th. More details about the program are coming soon.


Organizers: Pieter AbbeelPeter ChenDavid Silver, and Satinder Singh

Contact Us


         


Vote for Panel Discussion Questions here


Important Dates
Sunday October 9th, 2016: early paper submission deadline
Friday October 28th, 2016: early paper acceptance notification

Sunday November 6th, 2016: late submission deadline
Saturday November 26th, 2016: late paper acceptance notification


Friday December 9th, 2016: workshop 


Call for Papers

The deadline has passed.
We invite you to submit papers that combine neural networks with reinforcement learning, which will be presented as talks or posters. We will have two submissions deadlines: the early submission deadline is October 9th (midnight PST), and decisions will be sent out on October 28th. The later deadline is November 6th (midnight PST), and decisions will be sent out on November 26th. Please submit papers by email to this address.

Submissions should be in the NIPS 2016 format with a maximum of eight pages, not including references. The review process is double-blind.

Accepted submissions will be presented in the form of posters or contributed talks.


Abstract
Although the theory of reinforcement learning addresses an extremely general class of learning problems with a common mathematical formulation, its power has been limited by the need to develop task-specific feature representations. A paradigm shift is occurring as researchers figure out how to use deep neural networks as function approximators in reinforcement learning algorithms; this line of work has yielded remarkable empirical results in recent years. This workshop will bring together researchers working at the intersection of deep learning and reinforcement learning, and it will help researchers with expertise in one of these fields to learn about the other.


Schedule

09:00 - 09:30  Invited speaker - Rich SuttonLearning representations by stochastic gradient descent in cross-validation error

09:30 - 10:00 Contributed Talks - Session 1 (3 x 10mins)

                       1. Deep Successor Reinforcement Learning
                            Tejas D. Kulkarni, Ardavan Saeedi, Simanta Gautam, Samuel J. Gershman

                            2. An Actor-Critic Algorithm for Structured Prediction
                           Dzmitry Bahdanau, Philemon Brakel, Kelvin Xu, Anirudh Goyal, Ryan Lowe, Joelle Pineau, Aaron Courville, Yoshua Bengio

                            3. RL^2: Fast Reinforcement Learning via Slow Reinforcement Learning
                            Yan Duan, John Schulman, Xi Chen, Peter L. Bartlett, Ilya Sutskever, Pieter Abbeel

10:00 - 10:30  Invited speaker - John SchulmanThe Nuts and Bolts of Deep Reinforcement Learning Research

10:30 - 11:00 COFFEE

11:00 - 11:30 Invited speaker - Raia HadsellLearning to navigate

11:30 - 12:00 Contributed Talks - Session 2 (3 x 10mins)

                    1. Learning to Perform Physics Experiments via Deep Reinforcement Learning
                         Misha Denil, Pulkit Agrawal, Tejas D Kulkarni, Tom Erez, Peter Battaglia, Nando de Freitas

                        2. Sample-Efficient and Stable Deep Reinforcement Learning
                        Shixiang Gu, Sergey Levine, Ethan Holly, Timothy Lillicrap, Zoubin Ghahramani, Richard E. Turner

                        3. PGQ: Combining policy gradient and Q-learning
                        Brendan O'Donoghue, Remi Munos, Koray Kavukcuoglu, Volodymyr Mnih

12:00 - 12:30 Invited speaker - Chelsea FinnLarge-Scale Self-Supervised Robot Learning

12:30 - 13:30 LUNCH

13:30 - 14:00 Invited speaker - Josh TenenbaumChallenges for human-level learning in Deep RL

14:00 - 14:20 Contributed Talks - Session 3 (2 x 10mins)

                        1. Reinforcement Learning with Unsupervised Auxiliary Tasks
                        Max Jaderberg, Volodymyr Mnih, Wojciech Marian Czarnecki, Tom Schaul, Joel Z Leibo, David Silver, Koray Kavukcuoglu

                        2. Learning to Play in a Day: Faster Deep Reinforcement Learning by Optimality Tightening
                        Frank S. He, Yang Liu, Alexander G. Schwing, Jian Peng

14:20 - 14:30 Late breaking talk - Dave Silver, The Predictron: End-To-End Learning and Planning

14:30 - 15:30 Poster session 1 + COFFEE

15:30 - 15:45 Late breaking talk - Gabriel Dulac-ArnoldOptimizing Google Datacenters With RL

15:45 - 16:15 Invited speaker - Junhyuk Oh, Task Generalization via Deep Reinforcement Learning

16:15 - 16:45 Invited speaker - Nando de Freitas, Some Deep RL Research Frontiers

16:45 - 17:30 Panel discussion

17:30 - 18:30  Poster session 2


Contributed Papers


Accepted papers will be presented in a spotlight talk or a poster session.


Active One-shot Learning

Mark Woodward, Chelsea Finn


Guided Deep Reinforcement Learning for Additive Manufacturing Control Application

Amit Surana, Soumalya Sarkar, Kishore K. Reddy


Expert Level control of Ramp Metering based on Multi-task Deep Reinforcement Learning

Francois Belletti, Daniel Haziza, Gabriel Gomes, Joseph E. Gonzalez, Alexandre Bayen


Implicit ReasoNet: Modeling Large-Scale Structured Relationships with Shared Memory

Yelong Shen, Po-Sen Huang, Ming-Wei Chang, Jianfeng Gao


Reinforcement Learning for Transition-Based Mention Detection

Georgiana Dinu, Wael Hamza and Radu Florian


Language Expansion In Text-Based Games

Ghulam Ahmed Ansari, Sagar J P, Sarath Chandar, Balaraman Ravindran


Imitation Learning by Programs

Manav Choudhary, Gautham Muthuravichandran, Balaraman Ravindran


Deep Reinforcement Learning from Self-Play in Imperfect-Information Games

Johannes Heinrich, David Silver


Off-Policy Neural Fitted Actor-Critic

Matthieu Zimmer, Yann Boniface, Alain Dutech


Deep Reinforcement Learning with Averaged Target DQN

Oron Anschel, Nir Baram, Nahum Shimkin


Multi-task learning with deep model based reinforcement learning

Asier Mujika


Learning Locomotion Skills Using DeepRL: Does the Choice of Action Space Matter?

Xue Bin Peng, Glen Berseth, Michiel van de Panne


Learning to Learn for Global Optimization of Black Box Functions

Yutian Chen, Matthew W. Hoffman, Sergio Gomez Colmenarejo, Misha Denil, Timothy P. Lillicrap, Nando de Freitas


Hierarchical Object Detection with Deep Reinforcement Learning

Míriam Bellver Bueno, Xavier Giró-i-Nieto, Ferran Marqués, Jordi Torres


Learning to Play Guess Who? and Inventing a Grounded Language as a Consequence

Emilio Jorge, Mikael Kågebäck, Emil Gustavsson


Learning Runtime Parameters in Computer Systems with Delayed Experience Injection

Michael Schaarschmidt, Felix Gessert, Valentin Dalibard, Eiko Yoneki


Options discovery with budgeted reinforcement learning

Aurelia Leon, Ludovic Denoyer


Learning Visual Servoing with Deep Features and Trust Region Fitted Q-Iteration

Alex X. Lee, Sergey Levine, Pieter Abbeel


Off policy experience retention for deep actor critic learning

Tim de Bruin, Jens Kober, Karl Tuyls, Robert Babuška


Incorporating Human Domain Knowledge into Large Scale Cost Function Learning

Markus Wulfmeier, Dushyant Rao, Ingmar Posner


Unsupervised Learning of State Representations for Multiple Tasks

Antonin Raffin, Sebastian Hofer, Rico Jonschkowski, Oliver Brock, Freek Stulp


An Actor-Critic Algorithm for Structured Prediction

Dzmitry Bahdanau, Philemon Brakel, Kelvin Xu, Anirudh Goyal, Ryan Lowe, Joelle Pineau, Aaron Courville, Yoshua Bengio


Learning to Perform Physics Experiments via Deep Reinforcement Learning

Misha Denil, Pulkit Agrawal, Tejas D Kulkarni, Tom Erez, Peter Battaglia, Nando de Freitas


Deep Visual Foresight for Planning Robot Motion

Chelsea Finn, Sergey Levine


Deep Successor Reinforcement Learning

Tejas D. Kulkarni, Ardavan Saeedi, Simanta Gautam, Samuel J. Gershman


Deep Reinforcement Learning for Robotic Manipulation

Shixiang Gu, Ethan Holly, Timothy Lillicrap, Sergey Levine


Learning to Play in a Day: Faster Deep Reinforcement Learning by Optimality Tightening

Frank S. He, Yang Liu, Alexander G. Schwing, Jian Peng


RL^2: Fast Reinforcement Learning via Slow Reinforcement Learning

Yan Duan, John Schulman, Xi Chen, Peter L. Bartlett, Ilya Sutskever, Pieter Abbeel


Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic

Shixiang Gu, Timothy Lillicrap, Zoubin Ghahramani, Richard E. Turner, Sergey Levine


Reinforcement Learning with Unsupervised Auxiliary Tasks

Max Jaderberg, Volodymyr Mnih, Wojciech Marian Czarnecki, Tom Schaul, Joel Z Leibo, David Silver, Koray Kavukcuoglu


PGQ: Combining policy gradient and Q-learning

Brendan O'Donoghue, Remi Munos, Koray Kavukcuoglu, Volodymyr Mnih


Unifying Count-Based Exploration and Intrinsic Motivation

Marc Bellemare, Sriram Srinivasan, Georg Ostrovski, Tom Schaul, David Saxton, Remi Munos


Safe and efficient off-policy reinforcement learning

Remi Munos, Tom Stepleton, Anna Harutyunyan, Marc Bellemare


Learning from the Hindsight Plan -- Episodic MPC Improvement

Aviv Tamar, Garrett Thomas, Tianhao Zhang, Sergey Levine, Pieter Abbeel


Dialog Management with Deep Imitation Learning using Gated End-to-End Memory Networks

Julien Perez, Fei Liu


Information Theoretic MPC Using Neural Network Dynamics

Grady Williams, Nolan Wagener, Brian Goldfain, Paul Drews, James M. Rehg, Byron Boots, Evangelos A. Theodorou


Deep Reinforcement Learning for Tensegrity Robot Locomotion

Xinyang Geng, Marvin Zhang, Jonathan Bruce, Ken Caluwaerts, Massimo Vespignani, Vytas SunSpiral, Pieter Abbeel, Sergey Levine


Surprise-Based Intrinsic Motivation for Deep Reinforcement Learning

Joshua Achiam, Shankar Sastry


Multi-Objective Deep Reinforcement Learning

Hossam Mossalam, Yannis M. Assael, Diederik M. Roijers, Shimon Whiteson


#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning

Haoran Tang, Rein Houthooft, Davis Foote, Adam Stooke, Xi Chen, Yan Duan, John Schulman, Filip De Turck, Pieter Abbeel


Model-based Adversarial Imitation Learning

Nir Ben-Zrihen et al


Generalizing Skills with Semi-Supervised Reinforcement Learning

Chelsea Finn, Tianhe Yu, Justin Fu, Pieter Abbeel, Sergey Levine


Learning Modular Neural Network Policies for Multi-Task and Multi-Robot Transfer

Coline Devin, Abhishek Gupta, Trevor Darrell, Pieter Abbeel, Sergey Levine


Episodic Exploration for Deep Deterministic Policies for StarCraft Micromanagement

Nicolas Usunier, Gabriel Synnaeve, Zeming Lin, Soumith Chintala


A2T : Attend, Adapt and Transfer : Attentive Deep Architecture for Adaptive Transfer Learning from Multiple Sources

Janarthanan Rajendran, Aravind Lakshminarayanan, Mitesh M. Khapra, Prasanna P, Balaraman Ravindran


A Deep Hierarchical Approach to Lifelong Learning in Minecraft

Chen Tessler, Shahar Givony, Tom Zahavy, Daniel J. Mankowitz, Shie Mannor


Reset-Free Guided Policy Search: Efficient Deep Reinforcement Learning with Stochastic Initial States

Harley Montgomery, Anurag Ajay, Chelsea Finn, Pieter Abbeel, Sergey Levine


EPOpt: Learning Robust Neural Network Policies Using Model Ensembles

Aravind Rajeswaran, Sarvjeet Ghotra, Sergey Levine, Balaraman Ravindran


Continuous Action Reinforcement Learning with Input Convex Neural Networks

Brandon Amos, Lei Xu, J. Zico Kolter


Learning to Repeat: Fine Grained Action Repetition for Deep Reinforcement Learning

Sahil Sharma, Aravind S. Lakshminarayanan, Balaraman Ravindran


Stochastic Neural Networks for Hierarchical Reinforcement Learning

Carlos Florensa, Yan Duan, Pieter Abbeel


Modular Multitask Reinforcement Learning with Policy Sketches

Jacob Andreas, Dan Klein, Sergey Levine


Learning and Policy Search in Stochastic Dynamical Systems with Bayesian Neural Networks

Stefan Depeweg, José Miguel Hernández-Lobato, Finale Doshi-Velez, Steffen Udluft


Learning a Driving Simulator

Eder Santana, George Hotz


Towards Deep Symbolic Reinforcement Learning

Marta Garnelo, Kai Arulkumaran, Murray Shanahan


Generating Music by Fine-Tuning Recurrent Neural Networks with Reinforcement Learning

Natasha Jaques, Shixiang Gu, Richard E. Turner, Douglas Eck


Decoding multitask DQN in the world of Minecraft

Lydia Liu, Urun Dogan and Katja Hofmann


Inquire and Diagnose: Neural Symptom Checking Ensemble using Deep Reinforcement Learning

Kevin Tang, HaoCheng Kao, Jason Chou, Edward Chang


Grounded Semantic Networks for Learning Shared Communication Protocols

Matthew Hausknecht, Peter Stone


Exploration for Multi-task reinforcement learning with deep generative models

Saipraveen Bangaru, J S Suhas, Balaraman Ravindran


Multi-Agent Cooperation and the Emergence of (Natural) Language

Angeliki Lazaridou, Alexander Peysakhovich, Marco Baroni


Efficient Exploration for Dialogue Policy Learning with BBQ Networks & Replay Buffer Spiking

Zachary C. Lipton, Jianfeng Gao, Lihong Li, Xiujun Li, Faisal Ahmed, Li Deng


Deep learning approximation for stochastic control problems

Jiequn Han, Weinan E


Deep Reinforcement Learning for Multi-Domain Dialogue Systems

Heriberto Cuayáhuitl, Seunghak Yu, Ashley Williamson, Jacob Carse


Learning from the memory of Atari 2600

Jakub Sygnowski, Henryk Michalewski


Reinforcement Learning of POMDPs using Spectral Methods

Kamyar Azizzadenesheli, Alessandro Lazaric, Animashree Anandkumar


A K-fold Method for Baseline Estimation in Policy Gradient Algorithms

Nithyanand Kota, Abhishek Mishra, Sunil Srinivasa, Xi Chen, Pieter Abbeel


Investigating Recurrence and Eligibility Traces in Deep Q-Networks

Jean Harb, Doina Precup


Transfer Deep Reinforcement Learning in 3D Environments: An Empirical Study

Devendra Singh Chaplot, Guillaume Lample, Kanthashree Mysore Sathyendra, Ruslan Salakhutdinov


Collision Avoidance via Deep RL: Real Vision-Based Flight without a Single Real Image

Fereshteh Sadeghi, Sergey Levine


Learning Visual Servoing with Deep Features and Trust Region Fitted Q-Iteration

Alex X. Lee, Sergey Levine, Pieter Abbeel


A Differentiable Physics Engine for Deep Learning in Robotics

Jonas Degrave, Michiel Hermans, Joni Dambre, Francis Wyffels

Program Committee


Previous Deep RL Workshops
NIPS - December 2015
IJCAI - July 2016