# REPAINT: Knowledge Transfer in Deep Reinforcement Learning

arXiv: https://arxiv.org/abs/2011.11827 · HTML: https://mlsanity.com/paper/2011.11827/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Nov 2020.

## Built on by (most cited first, 14 of 14)

- [Robust Autonomy Emerges from Self-Play](https://mlsanity.com/paper/2502.03349/) (2025)
- [Cross-Domain Policy Adaptation via Value-Guided Data Filtering](https://mlsanity.com/paper/2305.17625/) (2023)
- [Multi-Agent Policy Transfer via Task Relationship Modeling](https://mlsanity.com/paper/2203.04482/) (2022)
- [A Taxonomy of Similarity Metrics for Markov Decision Processes](https://mlsanity.com/paper/2103.04706/) (2021)
- [Semantic-Aware Collaborative Deep Reinforcement Learning Over Wireless Cellular Networks](https://mlsanity.com/paper/2111.12064/) (2021)
- [Hybrid Transfer in Deep Reinforcement Learning for Ads Allocation](https://mlsanity.com/paper/2204.11589/) (2022)
- [Option Discovery Using LLM-guided Semantic Hierarchical Reinforcement Learning](https://mlsanity.com/paper/2503.19007/) (2025)
- [Towards Sample-Efficiency and Generalization of Transfer and Inverse Reinforcement Learning: A Comprehensive Literature Review](https://mlsanity.com/paper/2411.10268/) (2024)
- [Efficient Bayesian Policy Reuse with a Scalable Observation Model in Deep Reinforcement Learning](https://mlsanity.com/paper/2204.07729/) (2022)
- [Knowledge Transfer for Cross-Domain Reinforcement Learning: A Systematic Review](https://mlsanity.com/paper/2404.17687/) (2024)
- [Uncertainty-aware transfer across tasks using hybrid model-based successor feature reinforcement learning](https://mlsanity.com/paper/2310.10818/) (2023)
- [A Cantor-Kantorovich Metric Between Markov Decision Processes with Application to Transfer Learning](https://mlsanity.com/paper/2407.08324/) (2024)
- [Exploration in Knowledge Transfer Utilizing Reinforcement Learning](https://mlsanity.com/paper/2407.10835/) (2024)
- [Principled Fast and Meta Knowledge Learners for Continual Reinforcement Learning](https://mlsanity.com/paper/2603.00903/) (2026)

## Abstract (arXiv)

Accelerating learning processes for complex tasks by leveraging previously learned tasks has been one of the most challenging problems in reinforcement learning, especially when the similarity between source and target tasks is low. This work proposes REPresentation And INstance Transfer (REPAINT) algorithm for knowledge transfer in deep reinforcement learning. REPAINT not only transfers the representation of a pre-trained teacher policy in the on-policy learning, but also uses an advantage-based experience selection approach to transfer useful samples collected following the teacher policy in the off-policy learning. Our experimental results on several benchmark tasks show that REPAINT significantly reduces the total training time in generic cases of task similarity. In particular, when the source tasks are dissimilar to, or sub-tasks of, the target tasks, REPAINT outperforms other baselines in both training-time reduction and asymptotic performance of return scores.