Leveraging Sub-Optimal Data for Human-in-the-Loop Reinforcement Learning

arXiv:2405.00746v1 Announce Type: new
Abstract: To create useful reinforcement learning (RL) agents, step zero is to design a suitable reward function that captures the nuances of the task. However, reward engineering can be a difficult and time-consuming process. Instead, human-in-the-loop (HitL) RL allows agents to learn reward functions from human feedback. Despite recent successes, many of the HitL RL methods still require numerous human interactions to learn successful reward functions. To improve the feedback efficiency of HitL RL methods (i.e., …

abstract agents arxiv create cs.ai cs.lg cs.ro data design engineering feedback function functions hitl however human human feedback learn loop process reinforcement reinforcement learning type