Inductive Biases, Invariances and Generalization in RL (BIG)

International Conference on Machine Learning (ICML)

July 18, 2020

@BIGICML · #BIGICML

Contact: generalizationworkshop@gmail.com

For each paper being presented at the workshop, we will host (1) the pre-recorded presentation from SlidesLive, (2) a Rocket.Chat chatroom for text-based discussion, and (3) a Zoom meeting room. All of these can be found from each paper's landing page (which you can access by clicking on the title of the relevant paper).

The Zoom meeting rooms will be open only during the poster session timeslots (see the Schedule), during which authors will join the meeting rooms to allow you to ask them questions face-to-face. We encourage you to first watch the presentation associated with the paper, and then join the Zoom meeting room to ask questions and engage in further discussion.

Oral Presentation

Title	Authors	PDF	Zoom Links
Automatic Data Augmentation for Generalization in Reinforcement Learning	Roberta Raileanu, Max Goldstein, Denis Yarats, Ilya Kostrikov, Rob Fergus	PDF	Zoom
Off-Dynamics Reinforcement Learning Training for Transfer with Domain Classifiers	Benjamin Eysenbach, Swapnil Asawa, Ruslan Salakhutdinov, Shreyas Chaudhari, Sergey Levine	PDF	Zoom

Virtual Poster Session 1 (3:15 - 4:30am)

Title	Authors	PDF	Zoom Links
Learning Action Priors for Visuomotor transfer	Anurag Ajay, Pulkit Agrawal	PDF	Zoom
Spatially Structured Recurrent Modules	Nasim Rahaman, Anirudh Goyal, Muhammad Waleed Gondal, Manuel Wuthrich, Stefan Bauer, Yash Sharma, Yoshua Bengio, Bernhard Schölkopf	PDF	Zoom
Neural Dynamic Policies for End-to-End Sensorimotor Learning	Shikhar Bahl, Mustafa Mukadam, Abhinav Gupta, Deepak Pathak	PDF	Zoom
Hierarchical Alternative Training for Long Range Policy Transfer	Wei-Cheng Tseng, Jin-Siang Lin, Yao-Min Feng, Min Sun	PDF	Zoom
Meta-Reinforcement Learning for Robotic Industrial Insertion Tasks	Gerrit Schoettler, Ashvin Nair, Juan Aparicio Ojea, Sergey Levine, Eugen Solowjow	PDF	Zoom
Conditioning of Reinforcement Learning Agents and its Policy Regularization Application	Arip Asadulaev, Igor Kuznetsov, Gideon Stein, Andrey Filchenkov	PDF	Zoom
Robust Reinforcement Learning using Adversarial Populations	Eugene Vinitsky, Yuqing Du, Kanaad V Parvate, Kathy Jang, Pieter Abbeel, Alexandre Bayen	PDF	Zoom
Exact (Then Approximate) Dynamic Programming for Deep Reinforcement Learning	Henrik Marklund, Suraj Nair, Chelsea Finn	PDF	Zoom
A Differentiable Newton Euler Algorithm for Multi-body Model Learning	Michael Lutter, Johannes Silberbauer, Joe Watson, Jan Peters	PDF	Zoom
Towards Self-Paced Context Evaluation for Contextual Reinforcement Learning	Theresa Eimer, André Biedenkapp, Frank Hutter, Marius Lindauer	PDF	Zoom
Group Equivariant Deep Reinforcement Learning	Arnab Kumar Mondal, Pratheeksha Nair, Kaleem Siddiqi	PDF	Zoom
Towards TempoRL Learning When to Act	André Biedenkapp, Raghu Rajan, Frank Hutter, Marius Lindauer	PDF	Zoom
On the Equivalence of Bi-Level Optimization and Game-Theoretic Formulations of Invariant Risk Minimization	Kartik Ahuja, Karthikeyan Shanmugam, Kush Varshney, Amit Dhurandhar	PDF	Zoom
Learning Robust Representations with Score Invariant Learning	Daksh Idnani, Jonathan Kao	PDF	Zoom
Image Augmentation Is All You Need	Ilya Kostrikov, Denis Yarats, Rob Fergus	PDF	Zoom

Virtual Poster Session 2 (6:15 - 7:30am)

Title	Authors	PDF	Zoom Links
Reinforcement Learning Generalization with Surprise Minimization	Jerry Zikun Chen	PDF	Zoom
MOPO Model-based Offline Policy Optimization	Tianhe Yu, Garrett Thomas, Lantao Yu, Stefano Ermon, James Y. Zou, Sergey Levine, Chelsea Finn, Tengyu Ma	PDF	Zoom
Meta Attention Networks Meta Learning Attention To Modulate Information Between Sparsely Interacting Recurrent Modules	Kanika Madan, Nan Rosemary Ke, Anirudh Goyal, Yoshua Bengio	PDF	Zoom
Watch your Weight Reinforcement Learning	Robert Müller	PDF	Zoom
Learning to Learn from Failures Using Replay	Tao Chen, Pulkit Agrawal	PDF	Zoom
Fighting Copycat Agents in Behavioral Cloning From Multiple Observations	Chuan Wen, Jierui Lin, trevor darrell, Dinesh Jayaraman, Yang Gao (First two authors, contributed equally)	PDF	Zoom
Planning to Explore via Self-Supervised World Models	Ramanan Sekar, Oleh Rybkin, Kostas Daniilidis, Pieter Abbeel, Danijar Hafner, Deepak Pathak	PDF	Zoom
Structure Mapping for Transferability of Causal Models	Purva Pruthi, Javier González, Xiaoyu Lu, Madalina Fiterau	PDF	Zoom
Nesterov Momentum Adversarial Perturbations in the Deep Reinforcement Learning Domain	Ezgi Korkmaz	PDF	Zoom
Probing Dynamic Environments with Informed Policy Regularization	Pierre-Alexandre Kamienny, Matteo Pirotta, Alessandro Lazaric, Thibault Lavril, Nicolas Usunier, Ludovic Denoyer	PDF	Zoom
Counterfactual Transfer via Inductive Bias in Clinical Settings	Taylor W. Killian, Marzyeh Ghassemi, Shalmali Joshi	PDF	Zoom
Learning Invariant Representations for Reinforcement Learning without Reconstruction	Amy Zhang, Rowan Thomas McAllister, Roberto Calandra, Yarin Gal, Sergey Levine	PDF	Zoom
Model-based Adversarial Meta-Reinforcement Learning	Zichuan Lin, Garrett Thomas, Guangwen Yang, Tengyu Ma	PDF	Zoom
Multi-Task Reinforcement Learning as a Hidden-Parameter Block MDP	Amy Zhang, Shagun Sodhani, Khimya Khetarpal, Joelle Pineau	PDF	Zoom
Counterfactual Data Augmentation using Locally Factored Dynamics	Silviu Pitis, Elliot Creager, Animesh Garg	PDF	Zoom

Virtual Poster Session 3 (10:40 - 11:30am)

Title	Authors	PDF	Zoom Links
Evaluating Agents without Rewards	Brendon Matusch, Danijar Hafner, Jimmy Ba	PDF	Zoom
Bridging Worlds in Reinforcement Learning with Model-Advantage	Nirbhay Modhe, Harish K Kamath, Dhruv Batra, Ashwin Kalyan	PDF	Zoom
Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors	Karl Pertsch, Oleh Rybkin, Frederik Ebert, Chelsea Finn, Dinesh Jayaraman, Sergey Levine	PDF	Zoom
Efficient Imitation Learning with Local Trajectory Optimization	Jialin Song, Wenjie Jiang, Amir Yazdanbakhsh, Ebrahim Songhori, Anna Darling Goldie, Navdeep Jaitly, Azalia Mirhoseini	PDF	Zoom
Efficient Adaptation for End-to-End Vision-Based Robotic Manipulation	Ryan Julian, Benjamin Swanson, Gaurav S. Sukhatme, Sergey Levine, Chelsea Finn, Karol Hausman	PDF	Zoom
Learning Long-term Dependencies Using Cognitive Inductive Biases in Self-attention RNNs	Giancarlo Kerg, Bhargav Kanuparthi, Anirudh Goyal, Kyle Goyette, Yoshua Bengio, Guillaume Lajoie	PDF	Zoom
DisCor Corrective Feedback in Reinforcement Learning via Distribution Correction	Aviral Kumar, Abhishek Gupta, Sergey Levine	PDF	Zoom
One Solution is Not All You Need Few-Shot Extrapolation via Structured MaxEnt RL	Saurabh Kumar, Aviral Kumar, Sergey Levine, Chelsea Finn	PDF	Zoom
Attention Option-Critic	Raviteja Chunduru, Doina Precup	PDF	Zoom
Meta-Reinforcement Learning Robust to Distributional Shift via Model Identification and Experience Relabeling	Russell Mendonca, Xinyang Geng, Chelsea Finn, Sergey Levine	PDF	Zoom
PAC Imitation and Model-based Batch Learning of Contextual MDPs	Yash Nair, Finale Doshi-Velez	PDF	Zoom
Learning Off-Policy with Online Planning	Harshit Sikchi, Wenxuan Zhou, David Held	PDF	Zoom
If MaxEnt RL is the Answer, What is the Question?	Benjamin Eysenbach, Sergey Levine	PDF	Zoom
Discrete Planning with End-to-end Trained Neuro-algorithmic Policies	Marin Vlastelica Pogančić, Michal Rolinek, Georg Martius	PDF	Zoom
Maximum Entropy Model Rollouts Fast Model Based Policy Optimization without Compounding Errors	Chi Zhang, Sanmukh Rao Kuppannagari, Viktor Prasanna	PDF	Zoom