69 citations · 155 across the 24 of their papers we have counts for
6 papers · 1 filter
Mutual Information State Intrinsic Control
Rui Zhao, Yang Gao, Pieter Abbeel +2
Reinforcement learning has been shown to be highly successful at many challenging tasks. However, success heavily relies on well-shaped rewards. Intrinsically motivated RL attempts…
Generative Particle Variational Inference via Estimation of Functional Gradients
Neale Ratzlaff, Qinxun Bai, Li Fuxin +1
Recently, particle-based variational inference (ParVI) methods have gained interest because they can avoid arbitrary parametric assumptions that are common in variational inference…
Modeling Heterogeneous Statistical Patterns in High-dimensional Data by Adversarial Distributions: An Unsupervised Generative Framework
Han Zhang, Wenhao Zheng, Charley Chen +4
Since the label collecting is prohibitive and time-consuming, unsupervised methods are preferred in applications such as fraud detection. Meanwhile, such applications usually requi…
Feature Statistics Guided Efficient Filter Pruning
Hang Li, Chen Ma, Wei Xu +1
Building compact convolutional neural networks (CNNs) with reliable performance is a critical but challenging task, especially when deploying them in real-world applications. As a…
Mutual Information-based State-Control for Intrinsically Motivated Reinforcement Learning
Rui Zhao, Yang Gao, Pieter Abbeel +2
In reinforcement learning, an agent learns to reach a set of goals by means of an external reward signal. In the natural world, intelligent organisms learn from internal drives, by…
Implicit Generative Modeling for Efficient Exploration
Neale Ratzlaff, Qinxun Bai, Li Fuxin +1
Efficient exploration remains a challenging problem in reinforcement learning, especially for those tasks where rewards from environments are sparse. A commonly used approach for e…