Macro Action Reinforcement Learning with Sequence Disentanglement using Variational Autoencoder
This addresses the problem of high-dimensional action spaces in reinforcement learning for real-world applications, offering an incremental improvement over previous methods that relied on human-defined or repetitive macro actions.
The paper tackles the curse of dimensionality in reinforcement learning action spaces by introducing FaMARL, which autonomously learns disentangled factor representations to generate macro actions, achieving higher scores than other algorithms in environments requiring extensive search.
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.