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 gaming system (Stella), but adds support for continuous actions. This enables the benchmarking and evaluation of continuous-control agents (such as PPO [Schulman et al., 2017] and SAC [Haarnoja et al., 2018]) and value-based agents (such as DQN [Mnih et al., 2015] and Rainbow [Hessel et al., 2018]) on the same environment suite. We provide a series of open questions and research directions that CALE enables, as well as initial baseline results using Soft Actor-Critic. CALE is available as part of the ALE athttps://github.com/Farama-Foundation/Arcade-Learning-Environment.

翻译：我们介绍了连续街机学习环境（CALE），这是对著名的街机学习环境（ALE）[Bellemare等人，2013]的扩展。CALE使用相同的Atari 2600游戏系统（Stella）底层模拟器，但增加了对连续动作的支持。这使得可以在同一套环境上对连续控制智能体（如PPO [Schulman等人，2017]和SAC [Haarnoja等人，2018]）与基于价值的智能体（如DQN [Mnih等人，2015]和Rainbow [Hessel等人，2018]）进行基准测试和评估。我们提出了一系列CALE所启发的开放性问题与研究方向，并提供了使用Soft Actor-Critic的初步基线结果。CALE作为ALE的一部分可在https://github.com/Farama-Foundation/Arcade-Learning-Environment获取。