Tags » Reinforcement Learning

Bài toán Multi-armed bandit và reinforcement learning (1)

Trong bài viết này mình giới thiệu về bài toán Multi-armed bandit, về sự đánh đổi trong quá trình thăm dò và khai thác (exploration–exploitation trade-offs) của thuật toán để thông qua đó giảm thiếu chi phí thăm dò và tăng hiệu quả khai thác được. 1,903 more words

Reinforcement Learning

Evolving AI: Robots that can adapt like animals

The current hype around Artificial Intelligence (AI) does not seem to want a pause, but some reality check is due. Most of the time we are just talking about… 1,256 more words

Information Technology

On reinforcement learning

My first impression of RL comes from AlphaGo:


where policy and value networks are used. I realized this is a valuable idea since long term memory could be phrased and guide the behaviors, even at the sacrifice of suffering in the short term. 157 more words

Deep Learning

Long paper accepted for EACL 2017

Title: Tackling Error Propagation through Reinforcement Learning: A Case of Greedy Dependency Parsing

Conference: EACL 2017 (European Chapter of the Association for Computational Linguistics), at Valencia, 3-7 April 2017. 101 more words


2017 Trends -- What You Want & What Comes

Source: c’t Magazin für Computer Technik 3/17

[Vedio Source] [Article Source]

Don’t be worried about AI. A glance at the state of the art research shows that neural networks would still serve us, and artificial general intelligence is not yet in sight. 1,800 more words


Playing the Kaggle Two Sigma Challenge - Part 2


Last time I introduced the Kaggle Two Sigma Challenge and this time I’ll start describing what I did at the beginning of the competition. The competition started at the beginning of December, 2016 and completed on March 1, 2017.   1,202 more words

Artificial Intelligence