Safe exploration is a key to applying reinforcement learning (RL) in
saf...
We present Logical Optimal Actions (LOA), an action decision architectur...
Deep reinforcement learning (RL) methods often require many trials befor...
Conventional deep reinforcement learning methods are sample-inefficient ...
Unsupervised methods are promising for abstractive text summarization in...
Safe reinforcement learning has been a promising approach for optimizing...
We examine the problem of adversarial reinforcement learning for multi-a...
In many real-world applications (e.g., planetary exploration, robot
navi...