Tags » Reinforcement Learning

Dota 2 Bot by Open AI

Dota 2 Bot by Open AI

Our Dota 2 result shows that self-play can catapult the performance of machine learning systems from far below human level to superhuman, given sufficient compute.

31 more words

Supervised / Unsupervised / Reinforcement Learning


  • Supervised learning needs the input data which consists of questioning values and answering values to learn the truth.


Reinforcement Learning:

  • Reinforcement learning has to define rules like penalties and rewards to learn himself.

Learning how to Active Learn: A Deep Reinforcement Learning Approach

Meng Fang, Yuan Li, Trevor Cohn

(Submitted on 8 Aug 2017)

Active learning aims to select a small subset of data for annotation such that a classifier learned on the data is highly accurate. 98 more words

Machine Learning Frontier

Learning Policies for Adaptive Tracking with Deep Feature Cascades

Chen Huang, Simon Lucey, Deva Ramanan

(Submitted on 9 Aug 2017)

Visual object tracking is a fundamental and time-critical vision task. Recent years have seen many shallow tracking methods based on real-time pixel-based correlation filters, as well as deep methods that have top performance but need a high-end GPU. 163 more words

Machine Learning Frontier

There Are Many Interesting Things I

There’s a lot of interesting things in the software development and testing space, lots of stuff to study and learn. The past few years I spent learning to build automated checks in… 171 more words

Software Tester

Reinforcement learning for complex goals, using TensorFlow

Arthur Juliani

Reinforcement learning (RL) is about training agents to complete tasks. We typically think of this as being able to accomplish some goal. Take, for example, a robot we might want to train to open a door. 185 more words

Machine Learning Frontier

Deep Reinforcement Learning for Inquiry Dialog Policies with Logical Formula Embeddings

Takuya Hiraoka, Masaaki Tsuchida, Yotaro Watanabe

(Submitted on 2 Aug 2017)

This paper is the first attempt to learn the policy of an inquiry dialog system (IDS) by using deep reinforcement learning (DRL). 74 more words

Machine Learning Frontier