The most up-to-date list of publications can be found on my Google Scholar page. My extended CV is here.

Thesis

• Colas, Cédric. (2021). Towards Vygotskian Autotelic Agents: Learning Skills with Goals, Language and Intrinsically Motivated Deep Reinforcement Learning. Received the PhD Thesis Award 2022 from the French AI association. Slides of the PhD defense. Video.

Articles

Intrinsically Motivated Open-Ended Learning

• Colas, C., Karch, T., Moulin-Frier, C. & Oudeyer, P. Y. (2022). Vygotskian Autotelic Artificial Intelligence: Language and Culture Internalization for Human-Like AI. In review. Slides.
• Akakzia, A., Serris, O., Sigaud, 0. & Colas, C. (2022). Help Me Explore: Minimal Social Interventions for Graph-Based Autotelic Agents. In review. Code.
• Sigaud, O., Caselles-Dupré, H., Colas, C., Akakzia A., Oudeyer, P-Y. & Chetouani, M. (2021). Towards Teachable Autotelic Agents. In review.
• Colas, C., Karch, T., Sigaud, O. & Oudeyer, P-Y. (2021). Intrinsically Motivated Goal-Conditioned Reinforcement Learning: a Short Survey. Accepted to JAIR.
• Akakzia A., Colas, C., Oudeyer, P-Y., Chetouani, M. & Sigaud, O. (2020). Grounding Language to Autonomously-Acquired Skills via Goal Generation. Accepted at ICLR 2021. Code.
• Portelas, R., Colas, C., Weng, L., Hofmann, K., Oudeyer, P. Y. (2020). Automatic Curriculum Learning For Deep RL: A Short Survey. Accepted at IJCAI 2020. Talk.
• Colas, C., Karch, T., Lair, N., Dussoux, J. M., Moulin-Frier, C., Dominey, P. F., & Oudeyer, P. Y. (2020). Language as a Cognitive Tool to Imagine Goals in Curiosity-Driven Exploration. Accepted at NeurIPS 2020. Talk. Code.
• Lair, N., Colas, C., Portelas, R., Dussoux, J. M., Dominey, P. F., & Oudeyer, P. Y. (2019). Language Grounding through Social Interactions and Curiosity-Driven Multi-Goal Learning. Accepted at Visually Grounded Interaction and Language NeurIPS workshop, 2019.
• Portelas, R., Colas, C., Hofmann, K., & Oudeyer, P. Y. (2019). Teacher Algorithms for Curriculum Learning of Deep RL in Continuously Parameterized Environments. Accepted at CoRL 2019. Code.
• Colas, C., Sigaud, O., Oudeyer, P. Y. (2018). CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learning. Accepted at ICML 2019. Video. Talk. Code.
• Fournier, Colas, C., Chetouani, M., & P., Sigaud, O. (2019). CLIC: Curriculum Learning and Imitation for feature Control in non-rewarding environments. Accepted at IEEE Transactions on Cognitive and Developmental Systems.
• Colas, C., Sigaud, O., Oudeyer, P.. (2018). GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms. Accepted at ICML 2018. Talk. Code

Optimization and Epidemiology

• Colas, C., Hejblum, B., Rouillon, S., Thiébaut, R., Oudeyer, P-Y., Moulin-Frier, C. & Prague, M. (2020). EpidemiOptim: A Toolbox for the Optimization of Control Policies in Epidemiological Models. Accepted to JAIR. Slides. Demo. Code.

Evolutionary Computation

• Colas, C., Huizinga, J., Madhavan, V., & Clune, J. (2020). Scaling MAP-Elites to Deep Neuroevolution. Accepted at GECCO 2020. Slides. Talk. Code.

Statistics for RL

• Colas, C., Sigaud, O., Oudeyer, P. Y. (2019). A Hitchhiker’s Guide to Statistical Comparisons of Reinforcement Learning Algorithms. Code.
• Colas, C., Sigaud, O., Oudeyer, P. Y. (2018). How Many Random Seeds? Statistical Power Analysis in Deep Reinforcement Learning Experiments..

Brain-Computer Interfaces

• Ortega, P., Colas, C., & Faisal, A. A. (2018). Compact Convolutional Neural Networks for Multi-Class, Personalised, Closed-Loop EEG-BCI. In 2018 7th IEEE International Conference on Biomedical Robotics and Biomechatronics (Biorob) (pp. 136-141). IEEE.

Digital Art

• Colas, C. (2022). TastyPiano: A Subjective Sound–Taste Synesthetic Machine.