Macro Action Reinforcement Learning with Sequence Disentanglement using Variational Autoencoder.
Heecheol KimMasanori YamadaKosuke MiyoshiHiroshi YamakawaPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- action selection
- action space
- hidden state
- action sequences
- function approximation
- reward shaping
- optical flow
- state space
- partially observable domains
- learning algorithm
- reinforcement learning algorithms
- temporal difference
- transfer learning
- dynamic programming
- state action
- learning process
- multi agent
- computer vision