# KoGuN: Accelerating Deep Reinforcement Learning via Integrating Human Suboptimal Knowledge

arXiv: https://arxiv.org/abs/2002.07418 · HTML: https://mlsanity.com/paper/2002.07418/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Feb 2020.

## Built on by (most cited first, 13 of 13)

- [Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstraction](https://mlsanity.com/paper/2306.01439/) (2023)
- [PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration](https://mlsanity.com/paper/2203.08553/) (2022)
- [GALOIS: Boosting Deep Reinforcement Learning via Generalizable Logic Synthesis](https://mlsanity.com/paper/2205.13728/) (2022)
- [Neural Episodic Control with State Abstraction](https://mlsanity.com/paper/2301.11490/) (2023)
- [Flexible Attention-Based Multi-Policy Fusion for Efficient Deep Reinforcement Learning](https://mlsanity.com/paper/2210.03729/) (2022)
- [A Survey on Explainable Reinforcement Learning: Concepts, Algorithms, Challenges](https://mlsanity.com/paper/2211.06665/) (2022)
- [A Principle of Targeted Intervention for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2510.17697/) (2025)
- [System III: Learning with Domain Knowledge for Safety Constraints](https://mlsanity.com/paper/2304.11593/) (2023)
- [Ask-AC: An Initiative Advisor-in-the-Loop Actor-Critic Framework](https://mlsanity.com/paper/2207.01955/) (2022)
- [Heterogeneous Knowledge for Augmented Modular Reinforcement Learning](https://mlsanity.com/paper/2306.01158/) (2023)
- [Learning Individual Intrinsic Reward in Multi-Agent Reinforcement Learning via Incorporating Generalized Human Expertise](https://mlsanity.com/paper/2507.18867/) (2025)
- [A new soft computing method for integration of expert's knowledge in reinforcement learn-ing problems](https://mlsanity.com/paper/2106.07088/) (2021)
- [Computationally Efficient Reinforcement Learning: Targeted Exploration leveraging Simple Rules](https://mlsanity.com/paper/2211.16691/) (2022)

## Abstract (arXiv)

Reinforcement learning agents usually learn from scratch, which requires a large number of interactions with the environment. This is quite different from the learning process of human. When faced with a new task, human naturally have the common sense and use the prior knowledge to derive an initial policy and guide the learning process afterwards. Although the prior knowledge may be not fully applicable to the new task, the learning process is significantly sped up since the initial policy ensures a quick-start of learning and intermediate guidance allows to avoid unnecessary exploration. Taking this inspiration, we propose knowledge guided policy network (KoGuN), a novel framework that combines human prior suboptimal knowledge with reinforcement learning. Our framework consists of a fuzzy rule controller to represent human knowledge and a refine module to fine-tune suboptimal prior knowledge. The proposed framework is end-to-end and can be combined with existing policy-based reinforcement learning algorithm. We conduct experiments on both discrete and continuous control tasks. The empirical results show that our approach, which combines human suboptimal knowledge and RL, achieves significant improvement on learning efficiency of flat RL algorithms, even with very low-performance human prior knowledge.