Zobrazeno 1 - 10
of 51
pro vyhledávání: '"Colas, Cédric"'
Autor:
Perez, Jérémy, Léger, Corentin, Kovač, Grgur, Colas, Cédric, Molinaro, Gaia, Derex, Maxime, Oudeyer, Pierre-Yves, Moulin-Frier, Clément
As large language models (LLMs) start interacting with each other and generating an increasing amount of text online, it becomes crucial to better understand how information is transformed as it passes from one LLM to the next. While significant rese
Externí odkaz:
http://arxiv.org/abs/2407.04503
Modern AI systems such as self-driving cars and game-playing agents achieve superhuman performance, but often lack human-like features such as generalization, interpretability and human inter-operability. Inspired by the rich interactions between lan
Externí odkaz:
http://arxiv.org/abs/2405.04118
Autor:
Sigaud, Olivier, Baldassarre, Gianluca, Colas, Cedric, Doncieux, Stephane, Duro, Richard, Oudeyer, Pierre-Yves, Perrin-Gilbert, Nicolas, Santucci, Vieri Giuliano
A lot of recent machine learning research papers have ``open-ended learning'' in their title. But very few of them attempt to define what they mean when using the term. Even worse, when looking more closely there seems to be no consensus on what dist
Externí odkaz:
http://arxiv.org/abs/2311.00344
The ability to invent novel and interesting problems is a remarkable feature of human intelligence that drives innovation, art, and science. We propose a method that aims to automate this process by harnessing the power of state-of-the-art generative
Externí odkaz:
http://arxiv.org/abs/2310.10692
Autor:
Kovač, Grgur, Sawayama, Masataka, Portelas, Rémy, Colas, Cédric, Dominey, Peter Ford, Oudeyer, Pierre-Yves
Large Language Models (LLMs) are often misleadingly recognized as having a personality or a set of values. We argue that an LLM can be seen as a superposition of perspectives with different values and personality traits. LLMs exhibit context-dependen
Externí odkaz:
http://arxiv.org/abs/2307.07870
Autor:
Colas, Cédric, Teodorescu, Laetitia, Oudeyer, Pierre-Yves, Yuan, Xingdi, Côté, Marc-Alexandre
Humans learn to master open-ended repertoires of skills by imagining and practicing their own goals. This autotelic learning process, literally the pursuit of self-generated (auto) goals (telos), becomes more and more open-ended as the goals become m
Externí odkaz:
http://arxiv.org/abs/2305.12487
Autor:
Du, Yuqing, Watkins, Olivia, Wang, Zihan, Colas, Cédric, Darrell, Trevor, Abbeel, Pieter, Gupta, Abhishek, Andreas, Jacob
Reinforcement learning algorithms typically struggle in the absence of a dense, well-shaped reward function. Intrinsically motivated exploration methods address this limitation by rewarding agents for visiting novel states or transitions, but these m
Externí odkaz:
http://arxiv.org/abs/2302.06692
Publikováno v:
Nature Machine Intelligence 4, 1068-1076 (2022)
Building autonomous agents able to grow open-ended repertoires of skills across their lives is a fundamental goal of artificial intelligence (AI). A promising developmental approach recommends the design of intrinsically motivated agents that learn n
Externí odkaz:
http://arxiv.org/abs/2206.01134
In the quest for autonomous agents learning open-ended repertoires of skills, most works take a Piagetian perspective: learning trajectories are the results of interactions between developmental agents and their physical environment. The Vygotskian p
Externí odkaz:
http://arxiv.org/abs/2202.05129
Autor:
Sigaud, Olivier, Akakzia, Ahmed, Caselles-Dupré, Hugo, Colas, Cédric, Oudeyer, Pierre-Yves, Chetouani, Mohamed
Publikováno v:
Sigaud, O., Akakzia, A., Caselles-Dupr\'e, H., Colas, C., Oudeyer, P. Y., & Chetouani, M. (2022). Towards Teachable Autotelic Agents. IEEE Transactions on Cognitive and Developmental Systems
Autonomous discovery and direct instruction are two distinct sources of learning in children but education sciences demonstrate that mixed approaches such as assisted discovery or guided play result in improved skill acquisition. In the field of Arti
Externí odkaz:
http://arxiv.org/abs/2105.11977