4 papers
Safer Reinforcement Learning through Transferable Instinct Networks
Djordje Grbic, Sebastian Risi
Random exploration is one of the main mechanisms through which reinforcement learning (RL) finds well-performing policies. However, it can lead to undesirable or catastrophic outco…
Growing 3D Artefacts and Functional Machines with Neural Cellular Automata
Shyam Sudhakaran, Djordje Grbic, Siyan Li +4
Neural Cellular Automata (NCAs) have been proven effective in simulating morphogenetic processes, the continuous construction of complex structures from very few starting cells. Re…
EvoCraft: A New Challenge for Open-Endedness
Djordje Grbic, Rasmus Berg Palm, Elias Najarro +2
This paper introduces EvoCraft, a framework for Minecraft designed to study open-ended algorithms. We introduce an API that provides an open-source Python interface for communicati…
Safe Reinforcement Learning through Meta-learned Instincts
Djordje Grbic, Sebastian Risi
An important goal in reinforcement learning is to create agents that can quickly adapt to new goals while avoiding situations that might cause damage to themselves or their environ…