TY - GEN CY - Online Only A1 - Jiang, M A1 - Grefenstette, E A1 - Rocktäschel, T ID - discovery10132236 N2 - 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. UR - http://proceedings.mlr.press/v139/http://proceedings.mlr.press/v139/jiang21b.html PB - PMLR: Proceedings of Machine Learning Research N1 - This version is the version of record. For information on re-use, please refer to the publisher?s terms and conditions. TI - Prioritized Level Replay EP - 4950 SP - 4940 AV - public Y1 - 2021/// ER -