no code implementations • 14 May 2024 • Eleni Nisioti, Erwan Plantec, Milton Montero, Joachim Winther Pedersen, Sebastian Risi
Artificial neural networks (ANNs), on the other hand, are traditionally optimized in the space of weights.
no code implementations • 6 Apr 2024 • Joachim Winther Pedersen, Erwan Plantec, Eleni Nisioti, Milton Montero, Sebastian Risi
Artificial neural networks used for reinforcement learning are structurally rigid, meaning that each optimized parameter of the network is tied to its specific placement in the network structure.
2 code implementations • 9 Dec 2023 • Corentin Léger, Gautier Hamon, Eleni Nisioti, Xavier Hinaut, Clément Moulin-Frier
At the developmental scale, we employ these evolved reservoirs to facilitate the learning of a behavioral policy through Reinforcement Learning (RL).
no code implementations • 1 Nov 2023 • Richard Bornemann, Gautier Hamon, Eleni Nisioti, Clément Moulin-Frier
We further find that the agents learned collective exploration strategies extend to an open ended task setting, allowing them to solve task trees of twice the depth compared to the ones seen during training.
1 code implementation • 16 May 2023 • Eleni Nisioti, Clément Moulin-Frier
In this work, we study NC in simulation environments that consist of multiple, diverse niches and populations that evolve their plasticity, evolvability and niche-constructing behaviors.
1 code implementation • 18 Feb 2023 • Gautier Hamon, Eleni Nisioti, Clément Moulin-Frier
Neuroevolution (NE) has recently proven a competitive alternative to learning by gradient descent in reinforcement learning tasks.
no code implementations • 10 Jun 2022 • Eleni Nisioti, Mateo Mahaut, Pierre-Yves Oudeyer, Ida Momennejad, Clément Moulin-Frier
Comparing the level of innovation achieved by different social network structures across different tasks shows that, first, consistent with human findings, experience sharing within a dynamic structure achieves the highest level of innovation in tasks with a deceptive nature and large search spaces.
Cultural Vocal Bursts Intensity Prediction Reinforcement Learning (RL)
1 code implementation • 17 Feb 2022 • Eleni Nisioti, Clément Moulin-Frier
In this work, we study the interplay between environmental dynamics and adaptation in a minimal model of the evolution of plasticity and evolvability.
no code implementations • 20 Sep 2021 • Julius Taylor, Eleni Nisioti, Clément Moulin-Frier
In this work, we propose that aligning internal subjective representations, which naturally arise in a multi-agent setup where agents receive partial observations of the same underlying environmental state, can lead to more data-efficient representations.
no code implementations • 15 Dec 2020 • Eleni Nisioti, Clément Moulin-Frier
Recent advances in Artificial Intelligence (AI) have revived the quest for agents able to acquire an open-ended repertoire of skills.
no code implementations • 5 Jan 2020 • Eleni Nisioti, Nikolaos Thomos
We refer to our RNN architecture as Neural Density Evolution (NDE) and determine the weights of the RNN that correspond to optimal designs by minimizing a loss function that enforces the properties of asymptotically optimal design, as well as the desired structural characteristics of the code.