Imitation Refinement

A Bridge Connecting the Real and Idealized Worlds

We propose a novel approach of imitation refinement, which improves the quality of imperfect patterns, by mimicking the characteristics of ideal data. We demonstrate the effectiveness of imitation refinement on two real-world applications: in the first application, we show imitation refinement improves the quality of poorly written digits by imitating... [Read More]
Unsupervised Learning, My Papers

Multi-Armed Image Segmentation

We propose a novel framework for the problem of minimizing domain expert annotation time for image segmentation using two adversarial and complementary multi-armed agents. Specifically, the framework contains two reinforcement agents where one’s goal is to reinforce the segmentation model’s current knowledge, and the others goal is to exploit the... [Read More]
Semi-Supervised Learning, Reinforcement Learning, My Papers

How Does Value-Based Reinforcement Learning Find the Optimal Policy?

A General Explanation from Topological Point of View

DeepMind researchers claim state-of-the-art results in the Arcade Learning Environment in their recent ICML paper “A Distributional Perspective on Reinforcement Learning”. They investigate a distributional perspective of the value function in the reinforcement learning context and further design an algorithm applying Bellman’s equation to approximately learn value distributions, which results... [Read More]
Banach Fixed-Point Theorem, Reinforcement Learning, Paper Notes

Pedagogical Value-Aligned Crowdsourcing

Inspiring the Wisdom of Crowds via Interactive Teaching

Nowadays, crowdsourcing becomes an economical means to leverage human wisdom for large-scale data annotation. However, when annotation tasks require specific domain knowledge that people commonly don’t have, which is normal in citizen science projects, crowd workers’ integrity and proficiency problems will significantly impair the quality of crowdsourced data. In this... [Read More]
Human Computing, Interactive Teaching, Machine Teaching

Affordable On-line Dialogue Learning

Our new work extending the previous companion teaching framework for on-line dialogue policy learning has been accepted by the 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP 2017), which will be held in Copenhagen, Denmark, in September 2017. [Read More]
Dialogue Systems, Human-in-the-Loop, Reinforcement Learning, My Papers