Measuring Sample Efficiency and Generalization in Reinforcement Learning Benchmarks: NeurIPS 2020 Procgen Benchmark

TL;DR

This paper introduces a centralized benchmark for measuring sample efficiency and generalization in reinforcement learning, utilizing the Procgen environment to evaluate diverse algorithms in a scalable, standardized manner.

Contribution

It designs a scalable, standardized benchmark for assessing sample efficiency and generalization in reinforcement learning, facilitating progress measurement and comparison.

Findings

Top solutions demonstrated improved generalization capabilities.

Benchmark setup enabled comprehensive evaluation of diverse algorithms.

Analysis provided insights into strengths and weaknesses of competing methods.

Abstract

The NeurIPS 2020 Procgen Competition was designed as a centralized benchmark with clearly defined tasks for measuring Sample Efficiency and Generalization in Reinforcement Learning. Generalization remains one of the most fundamental challenges in deep reinforcement learning, and yet we do not have enough benchmarks to measure the progress of the community on Generalization in Reinforcement Learning. We present the design of a centralized benchmark for Reinforcement Learning which can help measure Sample Efficiency and Generalization in Reinforcement Learning by doing end to end evaluation of the training and rollout phases of thousands of user submitted code bases in a scalable way. We designed the benchmark on top of the already existing Procgen Benchmark by defining clear tasks and standardizing the end to end evaluation setups. The design aims to maximize the flexibility available for researchers who wish to design future iterations of such benchmarks, and yet imposes necessary practical constraints to allow for a system like this to scale. This paper presents the competition setup and the details and analysis of the top solutions identified through this setup in context of 2020 iteration of the competition at NeurIPS.