@inproceedings {pub6795,
	title = {Task-Specific Exploration in Meta-Reinforcement Learning via Task Reconstruction},
	author = {Radu Stoican AND Angelo Cangelosi AND Christian Goerick AND Thomas H Weisswange},
	year = {2026},
	month = {September},
	abstract = {Reinforcement learning trains policies specialized for a single task. Meta-reinforcement learning (meta-RL) improves upon this by leveraging prior experience to train policies for few-shot adaptation to new tasks. However, existing meta-RL approaches often struggle to explore and learn tasks effectively. We introduce a novel meta-RL algorithm that learns to learn task-specific exploration policies for sample-efficient few-shot adaptation. We achieve this through task reconstruction, an original method for learning to identify and collect small but informative datasets from tasks. To leverage these datasets, we also propose learning a meta-reward that encourages policies to learn to adapt. Empirical evaluations demonstrate that our algorithm achieves higher returns than existing meta-RL methods. Additionally, we show that even with full task information, adaptation is more challenging than previously assumed. However, policies trained with our meta-reward adapt to new tasks successfully.},
	publisher = {JMLR},
	url = {https://openreview.net/forum?id=VRRapVcaJH},
	note = {Published Papers Track. Original Publication: 
Stoican, R., Cangelosi, A., Goerick, C., \& Weisswange, T. H. (2026). Task-Specific Exploration in Meta-Reinforcement Learning via Task Reconstruction. Transactions on Machine Learning Research, 6318. },
	booktitle = {5th Conference on Lifelong Learning Agents (CoLLAs 2026): Published Papers Track},
	city = {Bucharest, Romania}
}