1
Pruning is a well-established technique for removing unnecessary structure from neural networks after training to improve the …
Metric-based meta-learning techniques have successfully been applied to few-shot classification problems. In this paper, we propose to …
In this work, we improve upon the stepwise analysis of noisy iterative learning algorithms initiated by Pensia, Jog, and Loh (2018) and …
Reward Machines (RMs) provide a structured, automata-based representation of a reward function that enables a Reinforcement Learning …
For embodied agents to infer representations of the underlying 3D physical world they inhabit, they should efficiently combine …
In this paper, we explore new approaches to combining information encoded within the learned representations of auto-encoders. We …
Recent works have shown that stochastic gradient descent (SGD) achieves the fast convergence rates of full-batch gradient descent for …
Markov Decision Processes (MDPs), the mathematical framework underlying most algorithms in Reinforcement Learning (RL), are often used …
We study the effect of the stochastic gradient noise on the training of generative adversarial networks (GANs) and show that it can …
Domain randomization is a popular technique for improving domain transfer, often used in a zero-shot setting when the target domain is …