# Towards Symbolic Reinforcement Learning with Common Sense

arXiv: https://arxiv.org/abs/1804.08597 · HTML: https://mlsanity.com/paper/1804.08597/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Apr 2018.

## Built on by (most cited first, 12 of 12)

- [Acquisition of Chess Knowledge in AlphaZero](https://mlsanity.com/paper/2111.09259/) (2021)
- [A Survey on Interpretable Reinforcement Learning](https://mlsanity.com/paper/2112.13112/) (2021)
- [A Survey on Neural-symbolic Learning Systems](https://mlsanity.com/paper/2111.08164/) (2021)
- [Neurosymbolic Reinforcement Learning and Planning: A Survey](https://mlsanity.com/paper/2309.01038/) (2023)
- [Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents](https://mlsanity.com/paper/2401.05821/) (2024)
- [Neuro-Symbolic AI: Explainability, Challenges, and Future Trends](https://mlsanity.com/paper/2411.04383/) (2024)
- [Symbolic Visual Reinforcement Learning: A Scalable Framework with Object-Level Abstraction and Differentiable Expression Search](https://mlsanity.com/paper/2212.14849/) (2022)
- [A Synergistic Approach In Network Intrusion Detection By Neurosymbolic AI](https://mlsanity.com/paper/2406.00938/) (2024)
- [Symbolic Distillation for Learned TCP Congestion Control](https://mlsanity.com/paper/2210.16987/) (2022)
- [Bridging the Gap: Representation Spaces in Neuro-Symbolic AI](https://mlsanity.com/paper/2411.04393/) (2024)
- [Short-Term-to-Long-Term Memory Transfer for Knowledge Graphs under Partial Observability](https://mlsanity.com/paper/2605.22142/) (2026)
- [Neuro-Symbolic Meta-Policies for Temporal Knowledge-Graph Memory under Partial Observability](https://mlsanity.com/paper/2607.18368/) (2026)

## Abstract (arXiv)

Deep Reinforcement Learning (deep RL) has made several breakthroughs in recent years in applications ranging from complex control tasks in unmanned vehicles to game playing. Despite their success, deep RL still lacks several important capacities of human intelligence, such as transfer learning, abstraction and interpretability. Deep Symbolic Reinforcement Learning (DSRL) seeks to incorporate such capacities to deep Q-networks (DQN) by learning a relevant symbolic representation prior to using Q-learning. In this paper, we propose a novel extension of DSRL, which we call Symbolic Reinforcement Learning with Common Sense (SRL+CS), offering a better balance between generalization and specialization, inspired by principles of common sense when assigning rewards and aggregating Q-values. Experiments reported in this paper show that SRL+CS learns consistently faster than Q-learning and DSRL, achieving also a higher accuracy. In the hardest case, where agents were trained in a deterministic environment and tested in a random environment, SRL+CS achieves nearly 100% average accuracy compared to DSRL's 70% and DQN's 50% accuracy. To the best of our knowledge, this is the first case of near perfect zero-shot transfer learning using Reinforcement Learning.