Reinforcement Learning in Latent Action Sequence Space
Heecheol Kim,Masanori Yamada,Kosuke Miyoshi,Tomoharu Iwata,Hiroshi Yamakawa,Heecheol Kim,Masanori Yamada,Kosuke Miyoshi,Tomoharu Iwata,Hiroshi Yamakawa
One problem in real-world applications of reinforcement learning is the high dimensionality of the action search spaces, which comes from the combination of actions over time. To reduce the dimensionality of action sequence search spaces, macro actions have been studied, which are sequences of primitive actions to solve tasks. However, previous studies relied on humans to define macro actions or a...
