CfP: GECCO 1st Evolutionary Reinforcement Learning Workshop

Less than a month before the deadline for the 1st Evolutionary Reinforcement Learning workshop @ GECCO 2021, the premiere conference in evolutionary computing (this year held virtually at Lille, France, from July 10-14, 2021)

In recent years reinforcement learning (RL) has received a lot of attention thanks to its performance and ability to address complex tasks. At the same time evolutionary algorithms (EA) have been proven to be competitive with standard RL algorithms on certain problems, while being simpler and more scalable.

Recent advances on EA have led to the development of algorithms like Novelty Search and Quality Diversity, capable of efficiently addressing complex exploration problems and finding a wealth of different policies. All these results and developments have sparked a strong renewed interest in such population-based computational approaches.

Nevertheless, even if EAs can perform well on hard exploration problems they still suffer from low sample efficiency. This limitation is less present in RL methods, notably because of sample reuse, while on the contrary they struggle with hard exploration settings. The complementary characteristics of RL algorithms and EAs have pushed researchers to explore new approaches merging the two in order to harness their respective strengths while avoiding their shortcomings.

The goal of the workshop is to foster collaboration, share perspectives, and spread best practices within our growing community at the intersection between RL and EA.


The topics at the heart of the workshop include:

  • Evolutionary reinforcement learning
  • Evolution strategies
  • Population-based methods for policy search
  • Neuroevolution
  • Hard exploration and sparse reward problems
  • Deceptive reward
  • Novelty and diversity search methods
  • Divergent search
  • Sample-efficient direct policy search
  • Intrinsic motivation, curiosity
  • Building or designing behaviour characterizations
  • Meta-learning, hierarchical learning
  • Evolutionary AutoML
  • Open-ended learning

Authors are invited to submit new original work, or new perspectives on recently published work  on those topics. Top submissions will be selected for oral presentation and be presented alongside keynote speaker Jeff Clune (ex-team leader at UberAI-Labs and current research team leader at OpenAI).

Important dates

  • Submission deadline: April 12, 2021
  • Notification: April 26, 2021
  • Camera-ready: May 3, 2021

You can find more info on the workshop website.