Text-based reinforcement learning agents have predominantly been neural
...
With the growing interest in large language models, the need for evaluat...
We introduce Logical Offline Cycle Consistency Optimization (LOCCO), a
s...
Nearly all general-purpose neural semantic parsers generate logical form...
Machine learning problems with multiple objective functions appear eithe...
We present Logical Optimal Actions (LOA), an action decision architectur...
Deep reinforcement learning (RL) methods often require many trials befor...
Text-based games (TBGs) have become a popular proving ground for the
dem...
Conventional deep reinforcement learning methods are sample-inefficient ...
In this paper, we present a novel image inpainting technique using frequ...
We present VisualHints, a novel environment for multimodal reinforcement...
We show that Reinforcement Learning (RL) methods for solving Text-Based ...
In this paper, we study the generalization properties of neural networks...
Image-based sports analytics enable automatic retrieval of key events in...
Image restoration is a technique that reconstructs a feasible estimate o...
Natural imitation in humans usually consists of mimicking visual
demonst...
We consider the problem of reinforcement learning under safety requireme...
Capturing and labeling camera images in the real world is an expensive t...
This paper is a contribution towards interpretability of the deep learni...
Reinforcement learning methods require careful design involving a reward...
Robotic learning in simulation environments provides a faster, more scal...
We present a conditional generative model that maps low-dimensional
embe...
We present a fully convolutional network(FCN) based approach for color i...