2019/03/22 by Hee‐Cheol Kim, Masanori Yamada, Kim, Heecheol +5 · 1 citation
Computer Science · Engineering · #Anomaly Detection Techniques and Applications #Applications (stat.AP) #Artificial Intelligence (cs.AI) #Autonomous Vehicle Technology and Safety #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Reinforcement Learning in Robotics #Robotics (cs.RO)
paper · pdf · doi:10.48550/arxiv.1903.09366
openalex publication_date 2019/03/22 · openalex created_date 2019/04/01 · openalex updated_date 2026/07/28
One problem in the application of reinforcement learning to real-world problems is the curse of dimensionality on the action space. Macro actions, a sequence of primitive actions, have been studied to diminish the dimensionality of the action space with regard to the time axis. However, previous studies relied on humans defining macro actions or assumed macro actions as repetitions of the same primitive actions. We present Factorized Macro Action Reinforcement Learning (FaMARL) which autonomously learns disentangled factor representation of a sequence of actions to generate macro actions that can be directly applied to general reinforcement learning algorithms. FaMARL exhibits higher scores than other reinforcement learning algorithms on environments that require an extensive amount of search.