Note: In light of the SARS-CoV-2/COVID-19 situation, the workshop will be held virtually. For more information, please see the ICML conference website.

​The submitted work should be between 4-8 pages (excluding references). Recently published (or under-review) work is also welcome. The submission should be in pdf format and should follow the style guidelines for ICML 2020 (found here). The review process is double-blind, and the work should be submitted by the latest 20th May 2020 10 June 2020, 11:59 PM (Anywhere on Earth). Submissions must be made using OpenReview.

There will be no formal publication of workshop proceedings. However, the accepted papers will be made available online on the workshop website. Best Student Papers will be considered for cash prizes.

The topics of interest include but not limited to:

  • Catastrophic forgetting
  • Capacity expansion techniques
  • Modularity and Compositionality for lifelong learning
  • Transfer Learning
  • Multi-task Learning
  • Curriculum Learning
  • Meta-Learning
  • New architectures for lifelong learning
  • Determine new, challenging benchmark domains
  • Using Hierarchical Abstractions to perform lifelong reinforcement learning (e.g., skills/options and state-space representations)