On RLC’s Outstanding Paper Awards

At RLC the “Outstanding Paper Award” will be different from what is traditionally done in machine learning conferences. We will not award papers for being the overall “best” papers in a conference; instead we will award papers for making significant contributions to specific aspects of research. We believe such an approach will be more inclusive–it will celebrate the diverse types of scientific contribution one can make in the field, and it will provide more equal opportunities for different types of papers to be awarded. The idea is to award papers for excelling in what they aimto accomplish.

It is commonly agreed that best paper awards are not necessarily a good predictor of impact in the future. We designed this award system with this in mind. Aligned with the RLC reviewing guidelines, this system tries not to award papers for the popularity of the topic they investigate, nor for their perceived novelty or potential future impact.

We are also hoping that this process will decouple scores and the likelihood of an award. Currently, in many systems, a single non-committal review can drastically reduce the chances of a paper receiving an award.

This system was designed to recognize and promote the diversity in our field. Papers that make meaningful contributions to real-world problems can be awarded in the same way that a purely theoretical paper can. Papers that close a gap in our understanding, or that report interesting negative results can also be recognized, or those that introduce a completely new perspective to the field. Finally, we also believe that the computational resources one has access to also should not change the likelihood of a paper receiving an award; thus there is a category for excelling in doing empirical research frugally.

There will be six award categories, they are the following (in alphabetical order):

• Outstanding Paper Award on Applications of Reinforcement Learning
• Outstanding Paper Award on Empirical Reinforcement Learning Research
• Outstanding Paper Award on Empirical Resourcefulness in Reinforcement Learning
• Outstanding Paper Award on Pioneering Vision in Reinforcement Learning
• Outstanding Paper Award on Scientific Understanding in Reinforcement Learning
• Outstanding Paper Award on the Theory of Reinforcement Learning

A more detailed description of each category is available at the end of this post. Importantly, no award is more prestigious than the other.

And how is this going to work?

In the review form, the technical reviewer and the senior reviewer will have to answer six yes/no questions in the form “Should this paper be nominated for the Outstanding Paper Award on X?”. These are not exclusive, so one paper can be nominated for more than one award. If the paper is nominated for any award, the nominator will be asked to write an additional paragraph justifying the nomination.

As discussed above, at RLC, the overall scores a paper receives will not necessarily determine whether the paper will receive an award or not. A paper might be accepted with a “Weak accept” but it may have excelled in a specific aspect captured by an award. We will encourage reviewers to nominate such papers. This approach is an attempt to decorrelate the noise from the review process from the award itself. As a concrete example, a paper might be accepted with a “Weak accept” because the reviewers recognize that the paper provides important theoretical results that tackles a major theoretical question in reinforcement learning, but these new results do not necessarily lead to major performance improvements (whether such a paper should receive a Strong Accept is beyond the scope of this post, we are simply acknowledging the noisiness of the process here). Such a paper should probably be nominated for the Outstanding Paper Award on the Theory of Reinforcement Learning.

Importantly, more than one paper can potentially receive the same award in a given year, and there might be years in which an award is not given.

We hope you find this interesting!

RLC Awards co-chairs

Roberta Raileanu & Marlos C. Machado

Description of Award Categories (Alphabetical Order)

Outstanding Paper Award on Applications of Reinforcement Learning

This award aims to acknowledge papers that demonstrate substantial progress on the application of reinforcement learning to complex, real-world problems. This award seeks to highlight groundbreaking work formulating real-world problems using the reinforcement learning framework, introducing a new application domain or challenge to reinforcement learning, or developing reinforcement learning methods that make significant progress on practical scenarios. The papers should display a notable level of practical utility and uphold a high standard of scientific rigor.

Outstanding Paper Award on Empirical Reinforcement Learning Research

This award recognizes papers that make significant contributions to the empirical aspects of reinforcement learning research. Examples include addressing fundamental practical challenges in reinforcement learning, introducing new empirical practices, methodologies, benchmarks, evaluation metrics, and visualization techniques, and providing tools and frameworks that will further enable empirical research. These papers should show a high standard of practical relevance and experimental rigor.

Outstanding Paper Award on Empirical Resourcefulness in Reinforcement Learning

This award honors papers that demonstrate resourcefulness in empirical research. These are papers that overcome the high computational cost of empirical research in reinforcement learning in ingenious ways, promoting more frugal empirical research. Examples include showcasing original, cost-effective methodologies, and resource-efficient experimental designs. The papers should embody high standards of creativity and practicality without sacrificing experimental rigor.

Outstanding Paper Award on Pioneering Vision in Reinforcement Learning

This award highlights papers that stand out with their forward-thinking vision and blue-sky ideas in the field of reinforcement learning. The papers awarded in this category will present groundbreaking, visionary ideas, theories, or techniques in reinforcement learning, potentially reshaping current perspectives or opening new avenues for research and applications. The papers must demonstrate originality, creativity, and the potential to inspire transformative advancements in reinforcement learning.

Outstanding Paper Award on Scientific Understanding in Reinforcement Learning

This award celebrates papers that significantly advance scientific understanding in the domain of reinforcement learning. It encourages the development of well-founded, clear understanding of the behavior of existing algorithms or the nuances of different problem formulations or different environments. Awarded papers will fill gaps in our understanding of the field; they will bring clarity to unexplored aspects of existing algorithms, they will provide evidence to dispute common assumptions, or they will better justify common practices in the field. They should also demonstrate excellence in scientific rigor and clarity of exposition, with very well-defined claims.

Outstanding Paper Award on the Theory of Reinforcement Learning

This award acknowledges papers that provide exceptional theoretical contributions to the field of reinforcement learning. Examples include theoretical unifications, new theoretical frameworks or formalisms, mathematical models, results, and theoretical insights into existing RL practices. The papers must exhibit a high level of technical proficiency and innovation.