Junhyuk Oh

Learn More
Motivated by vision-based reinforcement learning (RL) problems, in particular Atari games from the recent benchmark Aracade Learning Environment (ALE), we consider spatio-temporal prediction problems where future image-frames depend on control variables or actions as well as previous frames. While not composed of natural scenes, frames in Atari games are(More)
The network architectures of the proposed models and the baselines are illustrated in Figure 1. The weight of LSTM is initialized from a uniform distribution of [−0.08, 0.08]. The weight of the fully-connected layer from the encoded feature to the factored layer and from the action to the factored layer are initialized from a uniform distribution of [−1, 1](More)
In this paper, we introduce a new set of reinforcement learning (RL) tasks in Minecraft (a flexible 3D world). We then use these tasks to systematically compare and contrast existing deep reinforcement learning (DRL) architec-tures with our new memory-based DRL architec-tures. These tasks are designed to emphasize, in a controllable manner, issues that pose(More)
We propose a novel weakly-supervised semantic segmen-tation algorithm based on Deep Convolutional Neural Network (DCNN). Contrary to existing weakly-supervised approaches , our algorithm exploits auxiliary segmentation annotations available for different categories to guide seg-mentations on images with only image-level class labels. To make segmentation(More)
For all architectures, the first convolution layer consists of 32, 4 × 4, filters with a stride of 2 and a padding of 1. The second convolution layer consists of 64, 4 × 4, filters with a stride of 2 and a padding of 1. In Deep Q-Learning, batch size of 32 and discount factor of 0.99 are used. We used a replay memory size of 10 6 for random mazes and 5 × 10(More)
  • 1