Badger Seminar Summer 2021 Summary: Beyond Life-long Learning via Modular Meta-Learning
We recently held the Badger Seminar titled: Beyond Life-long Learning via Modular Meta-Learning, with participants joining online and at our headquarters in Prague.
GoodAI Scientist Nicholas Guttenberg wins the Evocraft Minecraft Open-Endedness Challenge
We are very proud that Nicholas Guttenberg, Senior Research Scientist at GoodAI, recently won the Evocraft 2021 competition - the Minecraft Open-Endedness Challenge!
GoodAI Research Roadmap 2021/2022
In 2021/22 GoodAI will focus on four core research areas: learning to learn, lifelong (gradual) learning, open-endedness, and generalization / extrapolation of meta-learned algorithms.
Improving parallelization in Space Engineers
Game developers at Keen Software House (sister company of GoodAI) have used Manual Badger architecture to evaluate parallelization techniques that would benefit the future development of Space Engineers.
Using open-ended algorithms to generate video game content in Space Engineers
Dr. Kai Arulkumaran of Araya has received a grant from GoodAI in order to apply open-ended algorithms to generating video game content (such as spaceships and space stations) in the sandbox game Space Engineers.
Solving generalization and making artificial intelligence curious
Researchers at Carnegie Mellon University (CMU)’s School of Computer Science in Pittsburgh are working on a project aiming to make artificial intelligence (AI) more resourceful and curious.
Bayesian Online Meta-Learning (BOML) for continual & gradual learning
New project aims to create AI that can continually acquire knowledge in different domains as well as utilize past experiences to quickly adapt to new unseen tasks.
GoodAI enters into research collaboration to progress meta-learning and combinatorial generalization
Self-improving artificial intelligence that can learn new tasks from small amounts of data is a crucial step for the advancement of strong artificial intelligence.
Creating a new framework for multi-agent AI systems
Current artificial intelligence is limited in its scope and is far from human-level intelligence. One of the key components missing is learning to pursue multiple goals, ones that are dynamic, changing, and that depend on knowledge acquired from previous tasks.
A new kind of open-ended environment for a new kind of artificial intelligence
If we are to develop artificial intelligence (AI) capable of learning as humans do, it needs to be tested in complex environments just like humans are.