Semantic Exploration from Language Abstractions and Pretrained Representations

Understand

Effective exploration is a challenge in reinforcement learning (RL).

• Novelty-based exploration methods can suffer in high-dimensional state spaces, such as continuous partially-observable 3D environments.
• We address this challenge by defining novelty using semantically meaningful state abstractions, which can be found in learned representations shaped by natural language.
• In particular, we evaluate vision-language representations, pretrained on natural image captioning datasets.