Publikation
HackAtari: Atari Learning Environments for Robust and Continual Reinforcement Learning
Quentin Delfosse; Jannis Blüml; Bjarne Gregori; Kristian Kersting
In: Computing Research Repository eprint Journal (CoRR), Vol. abs/2406.03997, Pages 1-32, arXiv, 2024.
Zusammenfassung
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 situa-
tions, 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 demon-
strate 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, causal RL, as well as LLM-driven RL. Our
work underscores the significance of developing interpretable in RL agents.