Organizers

Accepted Papers

Poster Session 1: 15:00 - 16:00

• "Unsupervised Learning of Image Embedding for Continuous Control" by Carlos Florensa, Jonas Degrave, Nicolas Heess, Jost Tobias Springenberg, Martin Riedmiller
• "Supervised Policy Update" by Quan Vuong, Yiming Zhang, Keith W. Ross
• "ARCHER: Aggressive Rewards to Counter Bias in Hindsight Experience Replay" by Sameera Lanka, Tianfu Wu
• "Competitive Experience Replay" by Hao Liu, Alexander Trott, Richard Socher, Caiming Xiong
• "Control What You Can: Intrinsically Motivated Hierarchical Reinforcement Learner" by Sebastian Blaes, Marin Vlastelica, Jia-Jie Zhu, Georg Martius
• "Cross-Task Knowledge Transfer for Visually-Grounded Navigation" by Devendra Singh Chaplot, Lisa Lee, Ruslan Salakhutdinov, Devi Parikh, Dhruv Batra
• "Deep Imitative Models for Flexible Inference, Planning, and Control" by Nicholas Rhinehart, Rowan McAllister, Sergey Levine
• "Residual Reinforcement Learning for Robot Control" by Tobias Johannink, Shikhar Bahl, Ashvin Nair, Jianlan Luo, Avinash Kumar, Matthias Loskyll, Juan Aparicio Ojea, Eugen Solowjow, Sergey Levine
• "Deep Counterfactual Regret Minimization" by Noam Brown, Adam Lerer, Sam Gross, Tuomas Sandholm
• "Option Discovery from Visual Features in Deep Reinforcement Learning" by Yang Xue, Yuhan Dong, Chunxiao Liu
• "Learning to Adapt in Dynamic, Real-World Environments via Meta-Reinforcement Learning" by Ignasi Clavera, Anusha Nagabandi, Simin Liu, Ronald S. Fearing, Pieter Abbeel, Sergey Levine, Chelsea Finn
• "Shrinkage-based Bias-Variance Trade-off for Policy Optimization" by Yihao Feng, Hao Liu, Jian Peng, Qiang Liu
• "Near-Optimal Representation Learning for Hierarchical Reinforcement Learning" by Ofir Nachum, Shixiang Gu, Honglak Lee, Sergey Levine
• "Visual imitation with a minimal adversary" by Scott Reed, Yusuf Aytar, Ziyu Wang, Alexander Novikov, Tom Paine, Sergio Gomez, David Budden, Tobias Pfaff, Aäron van den Oord, Oriol Vinyals
• "AD-VAT: An Asymmetric Dueling mechanism for learning Visual Active Tracking" by Fangwei Zhong , Peng Sun, Wenhan Luo, Tingyun Yan, Yizhou Wang
• "Target Driven Visual Navigation with Hybrid Asynchronous Universal Successor Representations" by Shamane Siriwardhana, Rivindu Weerasekera, Suranga Nanayakkara
• "Deep Curiosity Search: Intra-Life Exploration Can Improve Performance on Challenging Reinforcement Learning Problems" by Christopher Stanton, Jeff Clune
• "Towards a Simple Approach to Multi-step Model-based Reinforcement Learning" by Kavosh Asadi, Evan Cater, Dipendra Misra, Michael L. Littman
• "Generative Adversarial Self-Imitation Learning" by Junhyuk Oh, Yijie Guo, Satinder Singh, Honglak Lee
• "Reducing Sampling Error in the Monte Carlo Policy Gradient Estimator" by Josiah Hanna, Peter Stone
• "Interactive Agent Modeling by Learning to Probe" by Tianmin Shu, Caiming Xiong, Ying Nian Wu, Song-Chun Zhu
• "Deep Neuroevolution: Genetic Algorithms are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning" by Felipe Petroski Such, Vashisht Madhavan, Edoardo Conti, Joel Lehman, Kenneth O. Stanley, Jeff Clune
• "Distributed Deep Policy Gradient for Competitive Adversarial Environment" by Denis Osipychev, Seung Huyn, Girish Chowdhary
• "Kickstarting Deep Reinforcement Learning" by Simon Schmitt, Jonathan J. Hudson, Augustin Zidek, Simon Osindero, Carl Doersch, Wojciech M. Czarnecki, Joel Z. Leibo, Heinrich Kuttler, Andrew Zisserman, Karen Simonyan, S. M. Ali Eslami
• "Reinforcement Learning on Variable Impedance Controller for High-Precision Robotic Assembly" by Jianlan Luo, Eugen Solowjow, Chengtao Wen, Juan Aparicio, Aviv Tamar, Pieter Abbeel
• "Learning Dexterous In-Hand Manipulation" by Marcin Andrychowicz, Bowen Baker, Maciek Chociej, Rafal Jozefowicz, Bob McGrew, Jakub Pachocki, Arthur Petron, Matthias Plappert, Glenn Powell, Alex Ray, Jonas Schneider, Szymon Sidor, Josh Tobin, Peter Welinder, Lilian Weng, Wojciech Zaremba
• "Optimal Completion Distillation for Sequence Learning" by Sara Sabour, William Chan, Mohammad Norouzi
• "Learning Unsupervised Latent Dynamics Models from Pixels" by Danijar Hafner, Timothy Lillicrap, Ruben Villegas, Ian Fischer, David Ha, James Davidson
• "State-Covering Self-Supervised Reinforcement Learning" by Vitchyr Pong, Steven Lin, Murtaza Dalal, Ashvin Nair, Shikhar Bahl, Sergey Levine
• "Learning Goal Embeddings via Self-Play for Hierarchical Reinforcement Learning" by Sainbayar Sukhbaatar, Emily Denton, Arthur Szlam, Rob Fergus
• "Combined Reinforcement Learning via Abstract Representations" by Vincent Francois-Lavet, Yoshua Bengio, Doina Precup, Joelle Pineau
• "Equilibrium Finding via Asymmetric Self-Play Reinforcement Learning" by Jie Tang*, Keiran Paster*, Pieter Abbeel
• "ExpIt-OOS: Towards Learning from Planning in Imperfect Information Games" by Andy Kitchen, Michela Benedetti
• "Unsupervised Exploration with Deep Model-Based Reinforcement Learning" by Kurtland Chua, Rowan McAllister, Roberto Calandra, Sergey Levine
• "Multi-Preference Actor Critic" by Ishan Durugkar, Matthew Hausknecht, Adith Swaminathan, Patrick MacAlpine
• "Learning to Control Visual Abstractions for Structured Exploration in Deep Reinforcement Learning" by Catalin Ionescu, Tejas Kulkarni, Aäron van den Oord, Andriy Mnih, Vlad Mnih
• "MICE: Meta-Inverse Control with Events" by Avi Singh, Larry Yang, Chelsea Finn, Sergey Levine
• "Policy Gradient Search: Online Planning and Expert Iteration without Search Trees" by Thomas Anthony, Robert Nishihara, Philipp Moritz, Tim Salimans, John Schulman
• "Compression and Localization in Reinforcement Learning for ATARI Games" by Joel Ruben Antony Moniz, Barun Patra, Sarthak Garg
• "Reasoning About Physical Interactions with Object-Centric Models" by Michael Janner, Sergey Levine, William T. Freeman, Joshua B. Tenenbaum, Chelsea Finn, Jiajun Wu
• "Many-Goals Reinforcement Learning" by Vivek Veeriah, Junhyuk Oh, Satinder Singh
• "Contrasting Exploration in Parameter and Action Space: A Zeroth-Order Optimization Perspective" by Anirudh Vemula, Wen Sun, J. Andrew Bagnell
• "Human Interaction with Deep Reinforcement Learning Agents in Virtual Reality" by Lex Fridman, Henri Schmidt, Jack Terwilliger, Li Ding
• "DeepTraffic: Crowdsourced Hyperparameter Tuning of Deep Reinforcement Learning Systems for Multi-Agent Dense Traffic Navigation" by Lex Fridman, Jack Terwilliger, Benedikt Jenik
• "Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learning" by Jakob Foerster, Francis Song, Ed Hughes, Neil Burch, Iain Dunning, Shimon Whiteson, Matt Botvinick, Mike Bowling
• "Deep Reinforcement Learning and the Deadly Triad" by Hado van Hasselt, Yotam Doron, Florian Strub, Matteo Hessel, Nicolas Sonnerat, Joseph Modayil
• "Quinoa: a Q-function You Infer Normalized Over Actions" by Jonas Degrave, Abbas Abdolmaleki, Jost Tobias Springenberg, Nicolas Heess, Martin Riedmiller
• "Episodic Curiosity through Reachability" by Nikolay Savinov, Anton Raichuk, Raphaël Marinier, Damien Vincent, Marc Pollefeys, Timothy Lillicrap, Sylvain Gelly
• "Dexterous Manipulation with Deep Reinforcement Learning: Efficient, General, and Low-Cost" by Henry Zhu, Abhishek Gupta, Aravind Rajeswaran, Vikash Kumar, Sergey Levine
• "Toward Onboard Control System for Mobile Robots via Deep Reinforcement Learning" by Megumi Miyashita, Shirou Maruyama, Yasuhiro Fujita, Mitsuru Kusumoto, Tobias Pfeiffer, Eiichi Matsumoto, Ryosuke Okuta, Daisuke Okanohara
• "Prioritizing Starting States for Reinforcement Learning" by Arash Tavakoli*, Vitaly Levdik*, Riashat Islam, Petar Kormushev
• "KF-LAX: Kronecker-factored curvature estimation for control variate optimization in reinforcement learning" by Mohammad Firouzi
• "How to Organize your Deep Reinforcement Learning Agents: The Importance of Communication Topology" by Dhaval Adjodah, Dan Calacci, Abhimanyu Dubey, Peter Krafft, Esteban Moro, Alex Pentland
• "Transfer Value or Policy? A Value-centric Framework Towards Transferrable Continuous Reinforcement Learning" by Xingchao Liu, Tongzhou Mu, Hao Su
• "Flow Shape Design for Microfluidic Devices Using Deep Reinforcement Learning" by Xian Lee, Aditya Balu, Daniel Stoecklein, Baskar Ganapathysubramanian, Soumik Sarkar
• "Policy Optimization via Stochastic Recursive Gradient Algorithm" by Huizhuo Yuan, Junchi Li, Yuhao Tang, Yuren Zhou
• "Successor Uncertainties: exploration and uncertainty in temporal difference learning" by David Janz, Jiri Hron, José Miguel Hernández-Lobato, Katja Hofmann, Sebastian Tschiatschek
• "Deep Multi-Agent Reinforcement Learning with Relevance Graphs" by Aleksandra Malysheva, Tegg Taekyong Sung, Chae-Bong Sohn, Daniel Kudenko, Aleksei Shpilman
• "Sample-Efficient Imitation Learning via Generative Adversarial Nets" by Lionel Blondé, Alexandros Kalousis
• "Generalization and Regularization in DQN" by Jesse Farebrother, Marlos C. Machado, Michael Bowling
• "Learning To Activate Relay Nodes: Deep Reinforcement Learning Approach" by Minhae Kwon, Juhyeon Lee, Hyunggon Park
• "Predictor Corrector Policy Optimization" by Ching-An Cheng, Xinyan Yan, Nathan Ratliff, Byron Boots
• "Boosting Trust Region Policy Optimization with Normalizing Flows" by Yunhao Tang, Shipra Agrawal
• "Reinforcement Learning with Tensor State and Action Spaces" by Devin Schwab, Yifeng Zhu, Manuela Veloso
• "FoldingZero: Protein Folding from Scratch in Hydrophobic-Polar Model" by Yanjun Li, Hengtong Kang, Ketian Ye, Shuyu Yin, Xiaolin Li
• "Inverse reinforcement learning for video games" by Aaron Tucker, Adam Gleave, Stuart Russell
• "Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control" by Kendall Lowrey, Aravind Rajeswaran, Sham Kakade, Emanuel Todorov, Igor Mordatch
• "Learning Robotic Manipulation through Visual Planning and Acting" by Angelina Wang, Thanard Kurutach, Aviv Tamar, Pieter Abbeel
• "Unsupervised Object-Level Deep Reinforcement Learning" by William Agnew, Pedro Domingos

Poster Session 2: 17:15-18:15

• "Inverse Reinforcement Learning with Conditional Choice Probabilities" by Mohit Sharma, Joachim R. Groeger, Robert A. Miller, Kris M. Kitani
• "Variance Reduction for Reinforcement Learning in Input-Driven Environments" by Hongzi Mao, Shaileshh Bojja Venkatakrishnan, Malte Schwarzkopf, Mohammad Alizadeh
• "Curiosity-Driven Experience Prioritization via Density Estimation" by Rui Zhao, Volker Tresp
• "An Information-Theoretic Optimality Principle for Deep Reinforcement Learning" by Felix Leibfried, Jordi Grau-Moya, Haitham Bou-Ammar
• "Model-Based Regularization for Deep Reinforcement Learning with Transcoder Networks" by Felix Leibfried, Peter Vrancx
• "Solving the Rubik's Cube with Approximate Policy Iteration" by Stephen McAleer, Forest Agostinelli, Alexander Shmakov, Pierre Baldi
• "Q-map: a Convolutional Approach for Goal-Oriented Reinforcement Learning" by Fabio Pardo, Vitaly Levdik, Petar Kormushev
• "Generalization Tower Network: A Novel Deep Neural Network Architecture for Multi-Task Learning" by Yuhang Song, Mai Xu, Songyang Zhang, Liangyu Huo
• "Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow" by Xue Bin Peng , Angjoo Kanazawa, Sam Toyer, Pieter Abbeel, Sergey Levine
• "Backprop-Q: Generalized Backpropagation for Stochastic Computation Graphs" by Xiaoran Xu, Songpeng Zu, Yuan Zhang, Hanning Zhou, Wei Feng
• "Deep Quality-Value (DQV) Learning" by Matthia Sabatelli, Gilles Louppe, Pierre Geurts, Marco Alexander Wiering
• "The Termination Critic" by Anna Harutyunyan, Will Dabney, Diana Borsa, Nicolas Heess, Remi Munos, Doina Precup
• "Hindsight policy gradients" by Paulo Rauber, Avinash Ummadisingu, Filipe Mutz, Jürgen Schmidhuber
• "The Laplacian in RL: Learning Representations with Efficient Approximations" by Yifan Wu, George Tucker, Ofir Nachum
• "Multi-task Deep Reinforcement Learning with PopArt" by Matteo Hessel, Hubert Soyer, Lasse Espeholt, Wojciech Czarnecki, Simon Schmitt, Hado van Hasselt
• "Illuminating Generalization in Deep Reinforcement Learning through Procedural Level Generation" by Niels Justesen, Ruben Rodriguez Torrado, Philip Bontrager, Ahmed Khalifa, Julian Togelius, Sebastian Risi
• "Reinforcement Learning for Improving Agent Design" by David Ha
• "Importance Weighted Evolution Strategies" by Víctor Campos, Xavier Giro-i-Nieto, Jordi Torres
• "S-RL Toolbox: Environments, Datasets and Evaluation Metrics for State Representation Learning" by Antonin Raffin, Ashley Hill, René Traoré, Timothée Lesort, Natalia Dìaz-Rodrìguez, David Filliat
• "Visual Imitation Learning with Recurrent Siamese Networks" by Glen Berseth, Christopher J. Pal
• "Simulator Predictive Control: Using Learned Task Representations and MPC for Zero-Shot Generalization and Sequencing" by Zhanpeng He, Ryan Julian, Eric Heiden, Hejia Zhang, Stefan Schaal, Joseph Lim, Gaurav Sukhatme, Karol Hausman
• "Expert-augmented actor-critic for VIZDoom and Montezuma’s Revenge" by Michał Garmulewicz, Henryk Michalewski, Piotr Miłoś
• "Discretizing Continuous Action Space for On-Policy Optimization" by Yunhao Tang, Shipra Agrawal
• "Robot navigation using a variational dynamics model for state estimation and robust control" by Steven Bohez, Tim Verbelen, Sam Leroux, Elias De Coninck, Bert Vankeirsbilck, Pieter Simoens, Bart Dhoedt
• "Meta-Learning Language Guided Policy Learning" by John D Co-Reyes, Abhishek Gupta, Suvansh Sanjeev, Nick Altieri, John DeNero, Pieter Abbeel, Sergey Levine
• "ADC: A safe and sample efficient model-based reinforcement learning agent for dialogue systems" by Yen-Chen Wu, Bo-Hsiang Tseng, Paweł Budzianowski, Milica Gašić
• "CURIOUS: Intrinsically Motivated Multi-Task, Multi-Goal Reinforcement Learning" by Cédric Colas, Olivier Sigaud, Pierre-Yves Oudeyer
• "A Bandit Framework for Optimal Selection of Reinforcement Learning Agents" by Andreas Merentitis, Kashif Rasul, Roland Vollgraf, Abdul-Saboor Sheikh, Urs Bergmann
• "One-Shot High-Fidelity Imitation: Training Large-Scale Deep Nets with RL" by Tom Le Paine, Sergio Gomez Colmenarejo, Ziyu Wang, Scott Reed, Yusuf Aytar, Tobias Pfaff, Matt W. Hoffman, Gabriel Barth-Maron, Serkan Cabi, David Budden, Nando de Freitas
• "Deep Q-Learning Approaches to Dynamic Multi-Driver Dispatching and Repositioning" by John Holler, Zhiwei (Tony) Qin, Xiaocheng Tang, Yan Jiao, Tiancheng Jin, Satinder Singh, Chenxi Wang, Jieping Ye
• "Improving Coordination in Multi-Agent Deep Reinforcement Learning through Memory-driven Communication" by Emanuele Pesce, Giovanni Montana
• "Entropic Policy Composition with Generalized Policy Improvement and Divergence Correction" by Jonathan J Hunt, Andre Barreto, Timothy P Lillicrap, Nicolas Heess
• "Multi-agent Deep Reinforcement Learning with Extremely Noisy Observations" by Ozsel Kilinc, Giovanni Montana
• "Ranked Reward: Enabling Self-Play Reinforcement Learning for Combinatorial Optimization" by Alexandre Laterre, Yunguan Fu, Mohamed Khalil Jabri, Alain-Sam Cohen, David Kas, Karl Hajjar, Hui Chen, Torbjorn S. Dahl, Amine Kerkeni, Karim Beguir
• "SOLAR: Deep Structured Representations for Model-Based Reinforcement Learning" by Marvin Zhang*, Sharad Vikram*, Laura Smith, Pieter Abbeel, Matthew Johnson, Sergey Levine
• "Understanding Multi-Step Deep Reinforcement Learning: A Systematic Study of the DQN Target" by J. Fernando Hernandez-Garcia, Richard S. Sutton
• "Contingency-Aware Exploration in Reinforcement Learning" by Jongwook Choi*, Yijie Guo*, Marcin Moczulski*, Junhyuk Oh, Neal Wu, Mohammad Norouzi, Honglak Lee
• "Amortized Q-Learning" by Tom Van de Wiele, David Warde-Farley, Andriy Mnih, Volodymyr Mnih
• "Pseudo-Ground-Truth Training for Adversarial Text Generation with Reinforcement Learning" by Jonathan Sauder, Xiaoyin Che, Gonçalo Mordido, Haojin Yang, Christoph Meinel
• "Learning Montezuma's Revenge from a Single Demonstration" by Tim Salimans, Richard Chen
• "Unsupervised Control Through Non-Parametric Discriminative Rewards" by David Warde-Farley, Tom Van de Wiele, Tejas Kulkarni, Catalin Ionescu, Steven Hansen, Volodymyr Mnih
• "Actor-Expert: A Framework for using Action-Value Methods in Continuous Action Spaces" by Sungsu Lim, Ajin Joseph, Lei Le, Yangchen Pan, Martha White
• "What Would π* Do?: Imitation Learning via Off-Policy Reinforcement Learning" by Siddharth Reddy, Anca D. Dragan, Sergey Levine
• "Disentangling Controllable and Uncontrollable Factors by Interacting with the World" by Yoshihide Sawada, Luca Rigazio, Koji Morikawa, Masahiro Iwasaki, Yoshua Bengio
• "Time Reversal As Self-Supervision" by Suraj Nair, Mohammad Babaeizadeh, Chelsea Finn, Sergey Levine, Vikash Kumar
• "Internet Congestion Control via Deep Reinforcement Learning" by Nathan Jay, Noga H. Rotman, P. Brighten Godfrey, Michael Schapira, Aviv Tamar
• "Deep Online Learning via Meta-Learning: Continual Adaptation for Model-Based RL" by Anusha Nagabandi, Chelsea Finn, Sergey Levine
• "Learning Actionable Representations with Goal-Conditioned Policies" by Dibya Ghosh, Abhishek Gupta, Sergey Levine
• "Learning Deep Visuomotor Policies for Dexterous Hand Manipulation" by Divye Jain, Andrew Li, Shivam Singhal, Aravind Rajeswaran, Vikash Kumar, Emanuel Todorov
• "Object-Oriented Dynamics Learning through Multi-Level Abstraction" by Guangxiang Zhu, Jianhao Wang, Zhizhou Ren, Chongjie Zhang
• "Modulated Policy Hierarchies" by Alexander Pashevich, Danijar Hafner, James Davidson, Rahul Sukthankar, Cordelia Schmid
• "Relative entropy regularized policy iteration" by Abbas Abdolmaleki, Jost Tobias Springenberg, Jonas Degrave, Nicolas Heess, Martin Riedmiller
• "MaMiC : Macro and Micro Curriculum for Robotic Reinforcement Learning" by Manan Tomar, Akhil Sathuluri, Balaraman Ravindran
• "Improving Policy Generalization via Learning Domain Invariant Features with Adversarial Training" by Haiyan Yin, Jianda Chen, Sinno Jialin Pan
• "The Implicit Information in an Initial State" by Rohin Shah, Dmitrii Krasheninnikov, Jordan Alexander, Pieter Abbeel, Anca Dragan
• "An Atari Model Zoo for Analyzing, Visualizing, andComparing Deep Reinforcement Learning Agents" by Felipe Such, Vashish Madhavan, Rosanne Liu, Rui Wang, Pablo Castro, Yulun Li, Ludwig Schubert, Marc Bellemare, Jeff Clune, Joel Lehman
• "Model-Based Active Exploration in Reinforcement Learning" by Pranav Shyam, Wojciech Jaśkowski, Jürgen Schmidhuber, Faustino Gomez
• "Large-Scale Study of Curiosity-Driven Learning" by Yuri Burda*, Harri Edwards*, Deepak Pathak*, Amos Storkey, Trevor Darrell, Alexei A. Efros
• "Beyond Games: Bringing Exploration to Robots in Real-World" by Deepak Pathak, Dhiraj Gandhi, Abhinav Gupta
• "Achieving Gentle Manipulation with Deep Reinforcement Learning" by Sandy H. Huang, Martina Zambelli, Yuval Tassa, Jackie Kay, Murilo Martins, Patrick Pilarski, Raia Hadsell