Prioritized Level Replay

International Conference on Machine Learning (ICML)


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

ICML - July 18, 2021

Latency-Aware Neural Architecture Search with Multi-Objective Bayesian Optimization

David Eriksson, Pierce I-Jen Chuang, Samuel Daulton, Peng Xia, Akshat Shrivastava, Arun Babu, Shicong Zhao, Ahmed Aly, Ganesh Venkatesh, Maximilian Balandat

ICML - July 18, 2021

Variational Auto-Regressive Gaussian Processes for Continual Learning

Sanyam Kapoor, Theofanis Karaletsos, Thang D. Bui

ICCV - October 11, 2021

Contrast and Classify: Training Robust VQA Models

Yash Kant, Abhinav Moudgil, Dhruv Batra, Devi Parikh, Harsh Agrawal

ICCV - October 10, 2021

Revitalizing Optimization for 3D Human Pose and Shape Estimation: A Sparse Constrained Formulation

Taosha Fan, Kalyan Vasudev Alwala, Donglai Xiang, Weipeng Xu, Todd Murphey, Mustafa Mukadam

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