Pierre-Yves Oudeyer

8

Papers

13

Total Citations

Papers (8)

Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI

MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces

Hierarchically Organized Latent Modules for Exploratory Search in Morphogenetic Systems

Grounding Spatio-Temporal Language with Transformers

EAGER: Asking and Answering Questions for Automatic Reward Shaping in Language-guided RL

GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms

CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learning

Language as a Cognitive Tool to Imagine Goals in Curiosity Driven Exploration