1 code implementation • 17 Jul 2023 • Elias Najarro, Shyam Sudhakaran, Sebastian Risi
Biological nervous systems are created in a fundamentally different way than current artificial neural networks.
1 code implementation • NeurIPS 2023 • Shyam Sudhakaran, Miguel González-Duque, Claire Glanois, Matthias Freiberger, Elias Najarro, Sebastian Risi
MarioGPT can not only generate diverse levels, but can be text-prompted for controllable level generation, addressing one of the key challenges of current PCG techniques.
no code implementations • 31 Jan 2023 • Shyam Sudhakaran, Sebastian Risi
However many of these methods only optimize for high returns, and may not extract much information from a diverse dataset of trajectories.
no code implementations • 14 Jun 2022 • Kazuya Horibe, Kathryn Walker, Rasmus Berg Palm, Shyam Sudhakaran, Sebastian Risi
Biological systems are very robust to morphological damage, but artificial systems (robots) are currently not.
1 code implementation • 25 Apr 2022 • Elias Najarro, Shyam Sudhakaran, Claire Glanois, Sebastian Risi
In contrast to deep reinforcement learning agents, biological neural networks are grown through a self-organized developmental process.
1 code implementation • 25 Apr 2022 • Shyam Sudhakaran, Elias Najarro, Sebastian Risi
Inspired by cellular growth and self-organization, Neural Cellular Automata (NCAs) have been capable of "growing" artificial cells into images, 3D structures, and even functional machines.
1 code implementation • ICLR 2022 • Rasmus Berg Palm, Miguel González-Duque, Shyam Sudhakaran, Sebastian Risi
Additionally, we show that the VNCA can learn a distribution of stable attractors that can recover from significant damage.
no code implementations • 6 Apr 2021 • Kai Middlebrook, Shyam Sudhakaran, David Guy Brizan
MuSLCAT's backend is a modified version of BERT.
1 code implementation • 15 Mar 2021 • Shyam Sudhakaran, Djordje Grbic, Siyan Li, Adam Katona, Elias Najarro, Claire Glanois, Sebastian Risi
Neural Cellular Automata (NCAs) have been proven effective in simulating morphogenetic processes, the continuous construction of complex structures from very few starting cells.
1 code implementation • 30 Nov 2018 • Bohdan Khomtchouk, Shyam Sudhakaran
Zipf's law predicts a power-law relationship between word rank and frequency in language communication systems and has been widely reported in a variety of natural language processing applications.