# Efficient Exploration with Self-Imitation Learning via Trajectory-Conditioned Policy.

> Research article (arXiv (Cornell University), 2019) · cited 10× · AI/ML

**Wikidata**: [openalex:W2962719460](https://www.wikidata.org/wiki/openalex:W2962719460)  
**Source**: https://4ort.xyz/entity/efficient-exploration-with-self-imitation-learning-via-trajectory-conditioned-policy