Mathieu Rita

Artificial Intelligence (5) Core AI (5) Deep Learning (3) Machine Learning (3) Learning Types · Machine Learning (3) Models (2) Reinforcement Learning (1) Architectures (1) Learning Paradigms (1) Learning Types · Deep Learning (1) Methods (1)

emergent communication (4) multi-agent system (3) neural agent (3) referential game (2) reward model (1) speaker-listener game (1) reward overoptimization (1) emergent language (1) compositional language (1) zipf law of abbreviation (1) speaker-listener alignment (1) zipf law (1) large language model (1) neural network (1) discrete channel (1) language game (1) language emergence (1) message efficiency (1) co-adaptation loss (1) reward calibration (1)