Hackatari: Atari Learning Environments For Robust And Continual Reinforcement Learning

Abstract

Artificial agents' adaptability to novelty and alignment with intended behavior is crucial for their effective deployment. Reinforcement learning (RL) leverages novelty as a means of exploration, yet agents often struggle to handle novel situations, hindering generalization. To address these issues, we propose HackAtari, a framework introducing controlled novelty to the most common RL benchmark, the Atari Learning Environment. HackAtari allows us to create novel game scenarios (including simplification for curriculum learning), to swap the game elements' colors, as well as to introduce different reward signals for the agent. We demonstrate that current agents trained on the original environments include robustness failures, and evaluate HackAtari's efficacy in enhancing RL agents' robustness and aligning behavior through experiments using C51 and PPO. Overall, HackAtari can be used to improve the robustness of current and future RL algorithms, allowing Neuro-Symbolic RL, curriculum RL,

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keydelfosse2024hackatari

Related papers

• Toybox: Better Atari Environments For Testing Reinforcement Learning Agents (2018)0.00
• A Review For Deep Reinforcement Learning In Atari:benchmarks, Challenges, And Solutions (2021)0.00
• Robust Agents In Open-ended Worlds (2025)0.00
• Reward Learning From Human Preferences And Demonstrations In Atari (2018)0.00
• Model-based Reinforcement Learning For Atari (2019)0.00
• Is Deep Reinforcement Learning Really Superhuman On Atari? Leveling The Playing Field (2019)0.00
• Probing Transfer In Deep Reinforcement Learning Without Task Engineering (2022)0.00
• Toybox: A Suite Of Environments For Experimental Evaluation Of Deep Reinforcement Learning (2019)0.00