MiniWorld

Miniworld is a benchmark dataset that contains various environments used to evaluate in-context reinforcement learning methods, particularly their effectiveness and generalization capabilities.

Papers using MiniWorld (5)

Heuristic Transformer: Belief Augmented In-Context Reinforcement Learning2025Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success2025EDEN: Entorhinal Driven Egocentric Navigation Toward Robotic Deployment2025Enter the Void - Planning to Seek Entropy When Reward is Scarce2025Learning Successor Features the Simple Way2024