← Authors

Cédric Colas

12 papers · 2018–2025 · 5 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird 🌉 Interdisciplinary Bridge 🏃 Academic Marathon (7) 🐝 Cross-Pollinator (6) 🌈 Renaissance Researcher (7) 🗺️ Taxonomy Completionist (10) 🧭 Keyword Pioneer 🌍 Conference Polyglot (5) 🤝 Dynamic Duo (11) 📈 Trend Setter 💎 Century Club (12)

Conferences

ICML (5) NIPS (3) ICLR (2) CORL (1) IJCAI (1)

Top co-authors

Pierre-yves Oudeyer (11) Olivier Sigaud (4) Gaia Molinaro (3) Rémy Portelas (2) Katja Hofmann (2) Clément Moulin-Frier (2) Mohamed CHETOUANI (2) Julien Pourcel (2) Ahmed Akakzia (1) Abhishek Gupta (1)

Research topics

Generation (1)

Keywords

intrinsic motivation (4) deep reinforcement learning (3) curriculum learning (2) modular architecture (2) in-context learning (1) code generation (1) sample efficiency (1) latent learning (1) hierarchical reinforcement learning (1) exploration-exploitation tradeoff (1) autonomous learning (1) language understanding (1) generative model (1) gaussian mixture model (1) zero-shot generalization (1) language model (1) goal-conditioned policy (1) goal selection (1) procedural generation (1) policy gradient (1)

Papers

Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI ICML 2025
When LLMs Play the Telephone Game: Cultural Attractors as Conceptual Tools to Evaluate LLMs in Multi-turn Settings ICLR 2025
MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces ICML 2025
Latent Learning Progress Drives Autonomous Goal Selection in Human Reinforcement Learning NIPS 2024
ACES: Generating a Diversity of Challenging Programming Puzzles with Autotelic Generative Models NIPS 2024
Guiding Pretraining in Reinforcement Learning with Large Language Models ICML 2023
Grounding Language to Autonomously-Acquired Skills via Goal Generation ICLR 2021
Language as a Cognitive Tool to Imagine Goals in Curiosity Driven Exploration NIPS 2020
Automatic Curriculum Learning For Deep RL: A Short Survey IJCAI 2020
Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environments CORL 2019
CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learning ICML 2019
GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms ICML 2018