Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents

2017-09-18 · Marlos C. Machado, Marc G. Bellemare, Erik Talvitie, Joel Veness, Matthew Hausknecht, Michael Bowling

The Arcade Learning Environment (ALE) is an evaluation platform that poses the challenge of building AI agents with general competency across dozens of Atari 2600 games. It supports a variety of different problem settings and it has been receiving increasing attention from the scientific community, leading to some high-profile success stories such as the much publicized Deep Q-Networks (DQN). In this article we take a big picture look at how the ALE is being used by the research community. We show how diverse the evaluation methodologies in the ALE have become with time, and highlight some key concerns when evaluating agents in the ALE. We use this discussion to present some methodological best practices and provide new benchmark results using these best practices. To further the progress in the field, we introduce a new version of the ALE that supports multiple game modes and provides a form of stochasticity we call sticky actions. We conclude this big picture look by revisiting challenges posed when the ALE was introduced, summarizing the state-of-the-art in various problems and highlighting problems that remain open.

📄 PDF Abstract BibTeX arXiv:1709.06009

Code (7)

bclyang/updated-atari-env

floringogianu/atari-agents pytorch

glenn89/FederatedRL pytorch

jessefarebro/dqn-ale tf

link-kut/rl pytorch

mgbellemare/Arcade-Learning-Environment

openrlbenchmark/openrlbenchmark jax

Tasks

Atari Games

CALE: Continuous Arcade Learning Environment

2024-10-31 · Jesse Farebrother, Pablo Samuel Castro

We introduce the Continuous Arcade Learning Environment (CALE), an extension of the well-known Arcade Learning Environment (ALE) [Bellemare et al., 2013]. The CALE uses the same underlying emulator of the Atari 2600 gami…

Atari Games Benchmarking continuous-control Continuous Control

A Comparison of learning algorithms on the Arcade Learning Environment

2014-10-31 · Aaron Defazio, Thore Graepel

Reinforcement learning agents have traditionally been evaluated on small toy problems. With advances in computing power and the advent of the Arcade Learning Environment, it is now possible to evaluate algorithms on dive…

Atari Games reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

The Arcade Learning Environment: An Evaluation Platform for General Agents

2012-07-19 · Marc G. Bellemare, Yavar Naddaf, Joel Veness, Michael Bowling

In this article we introduce the Arcade Learning Environment (ALE): both a challenge problem and a platform and methodology for evaluating the development of general, domain-independent AI technology. ALE provides an int…

Atari Games Benchmarking Imitation Learning reinforcement-learning+3

Meta Arcade: A Configurable Environment Suite for Meta-Learning

2021-12-01 · Edward W. Staley, Chace Ashcraft, Benjamin Stoler, Jared Markowitz 외

Most approaches to deep reinforcement learning (DRL) attempt to solve a single task at a time. As a result, most existing research benchmarks consist of individual games or suites of games that have common interfaces but…

Deep Reinforcement Learning Meta-Learning Transfer Learning

AR as an Evaluation Playground: Bridging Metrics and Visual Perception of Computer Vision Models

2025-08-06 · Ashkan Ganj, Yiqin Zhao, Tian Guo arxiv

Quantitative metrics are central to evaluating computer vision (CV) models, but they often fail to capture real-world performance due to protocol inconsistencies and ground-truth noise. While visual perception studies ca…