Exploration in Approximate Hyper-State Space for Meta Reinforcement Learning

• Published in: arXiv.org
• Main Authors: Zintgraf, Luisa, Feng, Leo, Lu, Cong, Igl, Maximilian, Hartikainen, Kristian, Hofmann, Katja, Whiteson, Shimon
• Format: Paper Journal Article
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 09.06.2021
• Subjects: Computer Science - Artificial Intelligence; Computer Science - Learning; Exploration; Learning; Statistics - Machine Learning; Teaching methods; Training
• ISSN: 2331-8422
• DOI: 10.48550/arxiv.2010.01062

To rapidly learn a new task, it is often essential for agents to explore efficiently -- especially when performance matters from the first timestep. One way to learn such behaviour is via meta-learning. Many existing methods however rely on dense rewards for meta-training, and can fail catastrophically if the rewards are sparse. Without a suitable reward signal, the need for exploration during meta-training is exacerbated. To address this, we propose HyperX, which uses novel reward bonuses for meta-training to explore in approximate hyper-state space (where hyper-states represent the environment state and the agent's task belief). We show empirically that HyperX meta-learns better task-exploration and adapts more successfully to new tasks than existing methods.