CALE: Continuous Arcade Learning Environment

Abstract

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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyfarebrother2024cale

Code

• Farama-Foundation/Arcade-Learning-Environment—

Related papers

• Revisiting The Arcade Learning Environment: Evaluation Protocols And Open Problems For General Agents (2017)15.67
• Multiplayer Support For The Arcade Learning Environment (2020)0.00
• A Review For Deep Reinforcement Learning In Atari:benchmarks, Challenges, And Solutions (2021)0.00
• Contingency-aware Exploration In Reinforcement Learning (2018)0.00
• CORA: Benchmarks, Baselines, And Metrics As A Platform For Continual Reinforcement Learning Agents (2021)0.00
• Toybox: Better Atari Environments For Testing Reinforcement Learning Agents (2018)0.00
• Critic As Lyapunov Function (CALF): A Model-free, Stability-ensuring Agent (2024)0.00
• Hackatari: Atari Learning Environments For Robust And Continual Reinforcement Learning (2024)0.00