2024/08/12 by Mohit Jiwatode, Jiwatode, Mohit, Leon Schlecht +3
Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Neural and Evolutionary Computing (cs.NE) #Online Learning and Analytics
paper · pdf · doi:10.48550/arxiv.2408.06068
openalex publication_date 2024/08/12 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We propose RHEA CL, which combines Curriculum Learning (CL) with Rolling Horizon Evolutionary Algorithms (RHEA) to automatically produce effective curricula during the training of a reinforcement learning agent. RHEA CL optimizes a population of curricula, using an evolutionary algorithm, and selects the best-performing curriculum as the starting point for the next training epoch. Performance evaluations are conducted after every curriculum step in all environments. We evaluate the algorithm on the DoorKey and DynamicObstacles environments within the Minigrid framework. It demonstrates adaptability and consistent improvement, particularly in the early stages, while reaching a stable performance later that is capable of outperforming other curriculum learners. In comparison to other curriculum schedules, RHEA CL has been shown to yield performance improvements for the final Reinforcement learning (RL) agent at the cost of additional evaluation during training.