Press "Enter" to skip to content

Posts published in “Reinforcement learning”

Unity Machine Learning Agents. Super awesome, and quite scary.

Christoffer Björkskog 0

Unity has released a new SDK supporting machine learning agents in the Unity gaming engine. This enables you to: Study complex multi agent behaviors in realistic competitive and cooperative scenarios.…

Paper on Deep Reinforcement Learning

Christoffer Björkskog 0

Paper: A Brief Survey of Deep Reinforcement Learning Authors: Kai Arulkumaran, Marc Peter Deisenroth, Miles Brundage, Anil Anthony Bharath Submitted: Submitted on 19 Aug 2017 Read the PDF Abstract: Deep…

AI wins agains the best professional dota players

Christoffer Björkskog 0

OpenAi developed an AI that wins agains the best professional dota 2 players in the world in 1-on-1 games. It does not use imitation-learning or tree search to learn. Instead…

Feedback from humans to help machines learn

Christoffer Björkskog 0

Deep Mind and Open AI collaborated on an interesting project where they discovered how to use human feedback to help a deep learning algorithm learn by providing the reward feedback.…