Personalized Path Recourse for Reinforcement Learning Agents
This addresses the need for personalized corrective sequences in RL and supervised learning, though it appears incremental as it builds on existing recourse methods.
The paper tackles the problem of generating recourse paths for reinforcement learning agents to achieve better outcomes while maintaining similarity to original paths and personalizing to agent behavior, with results showing adaptation to different agents.
This paper introduces Personalized Path Recourse, a novel method that generates recourse paths for a reinforcement learning agent. The goal is to edit a given path of actions to achieve desired goals (e.g., better outcomes compared to the agent's original path) while ensuring a high similarity to the agent's original paths and being personalized to the agent. Personalization refers to the extent to which the new path is tailored to the agent's observed behavior patterns from their policy function. We train a personalized recourse agent to generate such personalized paths, which are obtained using reward functions that consider the goal, similarity, and personalization. The proposed method is applicable to both reinforcement learning and supervised learning settings for correcting or improving sequences of actions or sequences of data to achieve a pre-determined goal. The method is evaluated in various settings. Experiments show that our model not only recourses for a better outcome but also adapts to different agents' behavior.