Learning in Badger experts improves with episodic memory
AI agents often operate in partially observable environments, where only part of the environment state is visible at any given time. An agent in such an environment needs memory to compute effective actions from the history of its actions.
Read more
Historical Oranžérie opens in style
August 24, 2020
The grand opening of the newly refurbished historical building - The Oranžérie, recently took place in Prague. The building is now home to companies Keen Software House and GoodAI.
Read more
GoodAI Meta-learning & Multi-agent Learning Workshop attracts researchers from across the world
Last week GoodAI organized the first Meta-Learning & Multi-Agent Learning Workshop which throughout the week saw over 60 participants from across the world take part including speakers from Google Brain, DeepMind, OpenAI, University of Oxford, Stanford University and MIT.
Read more
GoodAI announces $300,000 AI Grant fund
August 10, 2020
Today we announced a $300,000 fund to support AI researchers who are pushing the boundaries of modern artificial intelligence.
Read more
Benefits of modular approach – generalization
One of the properties of the Badger architecture is modularity: instead of using one big neural network, the Badger should be composed of many small Experts which solve the whole task in a collaborative manner.
Read more
Workshop on Collective Meta-Learning and the Benefits of Deliberation
GoodAI recently hosted a virtual workshop with a number of external collaborators in order to address some of the crucial open questions related to our Badger Architecture.
Read more
Trainability of Badger – Why is Badger so hard to train?
To understand why Badger is hard to train, we need to understand first how Badger learns, using a toy task. We try to understand the plateaus, what happens during this period, and why the plateaus are there.
Read more
GoodAI’s ToyArchitecture published in PLOS ONE
Research in Artificial Intelligence (AI) has focused mostly on two extremes: either on small improvements in narrow AI domains, or on universal theoretical frameworks which are often uncomputable, or lack practical implementations.
Read more
Internal Badger Workshop – Summary
We recently organized an internal workshop with a number of external collaborators to advance the progress of various challenging topics related to the Badger architecture. In this post, we would like to share the outcomes of sessions.
Read more
5 ways COVID-19 is changing the future
The emergence and global spread of COVID-19 has already changed the world in ways that were unimaginable at the start of the year. However, in many areas, it seems to have sped up changes that were on the horizon anyway.
Read more