Goal Misgeneralization in Deep Reinforcement Learning
We study goal misgeneralization, a type of out-of-distribution generalization failure in reinforcement learning (RL). Goal misgeneralization failures occur when an RL agent retains its capabilities out-of-distribution yet pursues the wrong goal. For instance, an agent might continue to competently avoid obstacles, but navigate to the wrong place. In contrast, previous works have typically focused on capability generalization failures, where an agent fails to do anything sensible at test time. We formalize this distinction between capability and goal generalization, provide the first empirical demonstrations of goal misgeneralization, and present a partial characterization of its causes.
Code (4)
Tasks
Deep Reinforcement LearningNavigateOut-of-Distribution Generalizationreinforcement-learningReinforcement LearningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Mitigating Goal Misgeneralization via Minimax Regret
Safe generalization in reinforcement learning requires not only that a learned policy acts capably in new situations, but also that it uses its capabilities towards the pursuit of the designer's intended goal. The latter…
Reinforcement LearningReinforcement Learning from LLM Feedback to Counteract Goal Misgeneralization
We introduce a method to address goal misgeneralization in reinforcement learning (RL), leveraging Large Language Model (LLM) feedback during training. Goal misgeneralization, a type of robustness failure in RL occurs wh…
Language ModelingLanguage ModellingLarge Language Modelreinforcement-learning+2Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals
The field of AI alignment is concerned with AI systems that pursue unintended goals. One commonly studied mechanism by which an unintended goal might arise is specification gaming, in which the designer-provided specific…
Getting By Goal Misgeneralization With a Little Help From a Mentor
While reinforcement learning (RL) agents often perform well during training, they can struggle with distribution shift in real-world deployments. One particularly severe risk of distribution shift is goal misgeneralizati…
Reinforcement Learning (RL)Colour versus Shape Goal Misgeneralization in Reinforcement Learning: A Case Study
We explore colour versus shape goal misgeneralization originally demonstrated by Di Langosco et al. (2022) in the Procgen Maze environment, where, given an ambiguous choice, the agents seem to prefer generalization based…
reinforcement-learning