Representation learning for control
Kevin James Doty · 2019
State representation learning finds an embedding from a high dimensional observation space to a lower dimensional and information dense state space, without supervision. Effective state representation learning can improve the sample efficiency and stability of downstream tasks such as reinforcement learning for control. In this work, two autoencoder variants and two inverse models are explored as representation learning architectures. The DQN algorithm is used to learn control in the resulting latent spaces. Latent-control performance is benchmarked against a standard fully convolutional DQN on a downstream control task.