Publication

Prioritized Level Replay

International Conference on Machine Learning (ICML)


Abstract

Environments with procedurally generated content serve as important benchmarks for testing systematic generalization in deep reinforcement learning. In this setting, each level is an algorithmically created environment instance with a unique configuration of its factors of variation. Training on a prespecified subset of levels allows for testing generalization to unseen levels. What can be learned from a level depends on the current policy, yet prior work defaults to uniform sampling of training levels independently of the policy. We introduce Prioritized Level Replay (PLR), a general framework for selectively sampling the next training level by prioritizing those with higher estimated learning potential when revisited in the future. We show TD-errors effectively estimate a level’s future learning potential and, when used to guide the sampling procedure, induce an emergent curriculum of increasingly difficult levels. By adapting the sampling of training levels, PLR significantly improves sample efficiency and generalization on Procgen Benchmark—matching the previous state-of-the-art in test return—and readily combines with other methods. Combined with the previous leading method, PLR raises the state-of-the-art to over 76% improvement in test return relative to standard RL baselines. Our code is available at: Github.

Related Publications

All Publications

SIGDIAL - August 1, 2021

Annotation Inconsistency and Entity Bias in MultiWOZ

Kun Qian, Ahmad Berrami, Zhouhan Lin, Ankita De, Alborz Geramifard, Zhou Yu, Chinnadhurai Sankar

arxiv - November 1, 2020

The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes

Douwe Kiela, Hamed Firooz, Aravind Mohan, Vedanuj Goswami, Amanpreet Singh, Pratik Ringshia, Davide Testuggine

ICML - July 24, 2021

Using Bifurcations for Diversity in Differentiable Games

Jonathan Lorraine, Jack Parker-Holder, Paul Vicol, Aldo Pacchiano, Luke Metz, Tal Kachman, Jakob Foerster

arXiv - July 8, 2021

First-Generation Inference Accelerator Deployment at Facebook

Michael Anderson, Benny Chen, Stephen Chen, Summer Deng, Jordan Fix, Michael Gschwind, Aravind Kalaiah, Changkyu Kim, Jaewon Lee, Jason Liang, Haixin Liu, Yinghai Lu, Jack Montgomery, Arun Moorthy, Satish Nadathur, Sam Naghshineh, Avinash Nayak, Jongsoo Park, Chris Petersen, Martin Schatz, Narayanan Sundaram, Bangsheng Tang, Peter Tang, Amy Yang, Jiecao Yu, Hector Yuen, Ying Zhang, Aravind Anbudurai, Vandana Balan, Harsha Bojja, Joe Boyd, Matthew Breitbach, Claudio Caldato, Anna Calvo, Garret Catron, Sneh Chandwani, Panos Christeas, Brad Cottel, Brian Coutinho, Arun Dalli, Abhishek Dhanotia, Oniel Duncan, Roman Dzhabarov, Simon Elmir, Chunli Fu, Wenyin Fu, Michael Fulthorp, Adi Gangidi, Nick Gibson, Sean Gordon, Beatriz Padilla Hernandez, Daniel Ho, Yu-Cheng Huang, Olof Johansson, Shishir Juluri, Shobhit Kanaujia, Manali Kesarkar, Jonathan Killinger, Ben Kim, Rohan Kulkarni, Meghan Lele, Huayu Li, Huamin Li, Yueming Li, Cynthia Liu, Jerry Liu, Bert Maher, Chandra Mallipedi, Seema Mangla, Kiran Kumar Matam, Jubin Mehta, Shobhit Mehta, Christopher Mitchell, Bharath Muthiah, Nitin Nagarkatte, Ashwin Narasimha, Bernard Nguyen, Thiara Ortiz, Soumya Padmanabha, Deng Pan, Ashwin Poojary, Ye (Charlotte) Qi, Olivier Raginel, Dwarak Rajagopal, Tristan Rice, Craig Ross, Nadav Rotem, Scott Russ, Kushal Shah, Baohua Shan, Hao Shen, Pavan Shetty, Krish Skandakumaran, Kutta Srinivasan, Roshan Sumbaly, Michael Tauberg, Mor Tzur, Hao Wang, Man Wang, Ben Wei, Alex Xiao, Chenyu Xu, Martin Yang, Kai Zhang, Ruoxi Zhang, Ming Zhao, Whitney Zhao, Rui Zhu, Lin Qiao, Misha Smelyanskiy, Bill Jia, Vijay Rao

To help personalize content, tailor and measure ads, and provide a safer experience, we use cookies. By clicking or navigating the site, you agree to allow our collection of information on and off Facebook through cookies. Learn more, including about available controls: Cookies Policy