# Online inductive learning from answer sets for efficient reinforcement learning exploration

arXiv: https://arxiv.org/abs/2501.07445 · HTML: https://mlsanity.com/paper/2501.07445/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Interpretable and logic-guided RL, one of 15 directions in Deep reinforcement learning methods.
- Builds on 16 of its 31 references that are in the map.
- First posted on arXiv 13 Jan 2025.

## Placed in

- Deep reinforcement learning methods / [Interpretable and logic-guided RL](https://mlsanity.com/deeprl/interpretable-and-logic-guided-rl/)

## Builds on (most cited first, 16 of 16)

- [Deep Reinforcement Learning with Double Q-learning](https://mlsanity.com/paper/1509.06461/) (2015)
- [Learning programs by learning from failures](https://mlsanity.com/paper/2005.02259/) (2020)
- [Foundations for Restraining Bolts: Reinforcement Learning with LTLf/LDLf restraining specifications](https://mlsanity.com/paper/1807.06333/) (2018)
- [Heuristic-Guided Reinforcement Learning](https://mlsanity.com/paper/2106.02757/) (2021)
- [Symbols as a Lingua Franca for Bridging Human-AI Chasm for Explainable and Advisable AI Systems](https://mlsanity.com/paper/2109.09904/) (2021)
- [Neural Markov Logic Networks](https://mlsanity.com/paper/1905.13462/) (2019)
- [Induction and Exploitation of Subgoal Automata for Reinforcement Learning](https://mlsanity.com/paper/2009.03855/) (2020)
- [Learning First-Order Representations for Planning from Black-Box States: New Results](https://mlsanity.com/paper/2105.10830/) (2021)
- [Inductive Learning of Answer Set Programs from Noisy Examples](https://mlsanity.com/paper/1808.08441/) (2018)
- [Randomised Gaussian Process Upper Confidence Bound for Bayesian Optimisation](https://mlsanity.com/paper/2006.04296/) (2020)
- [Deep Explainable Relational Reinforcement Learning: A Neuro-Symbolic Approach](https://mlsanity.com/paper/2304.08349/) (2023)
- [REBA: A Refinement-Based Architecture for Knowledge Representation and Reasoning in Robotics](https://mlsanity.com/paper/1508.03891/) (2015)
- [Logic programming for deliberative robotic task planning](https://mlsanity.com/paper/2301.07550/) (2023)
- [Online Safety Property Collection and Refinement for Safe Deep Reinforcement Learning in Mapless Navigation](https://mlsanity.com/paper/2302.06695/) (2023)
- [Learning Logic Specifications for Soft Policy Guidance in POMCP](https://mlsanity.com/paper/2303.09172/) (2023)
- [Learning Logic Specifications for Policy Guidance in POMDPs: an Inductive Logic Programming Approach](https://mlsanity.com/paper/2402.19265/) (2024)

## Built on by (most cited first, 4 of 4)

- [Learning Symbolic Persistent Macro-Actions for POMDP Solving Over Time](https://mlsanity.com/paper/2505.03668/) (2025)
- [Sample-Efficient Neurosymbolic Deep Reinforcement Learning](https://mlsanity.com/paper/2601.02850/) (2026)
- [Sample-efficient Neuro-symbolic Proximal Policy Optimization](https://mlsanity.com/paper/2604.25534/) (2026)
- [Explaining Reinforcement Learning Agents via Inductive Logic Programming](https://mlsanity.com/paper/2607.13655/) (2026)

## Abstract (arXiv)

This paper presents a novel approach combining inductive logic programming with reinforcement learning to improve training performance and explainability. We exploit inductive learning of answer set programs from noisy examples to learn a set of logical rules representing an explainable approximation of the agent policy at each batch of experience. We then perform answer set reasoning on the learned rules to guide the exploration of the learning agent at the next batch, without requiring inefficient reward shaping and preserving optimality with soft bias. The entire procedure is conducted during the online execution of the reinforcement learning algorithm. We preliminarily validate the efficacy of our approach by integrating it into the Q-learning algorithm for the Pac-Man scenario in two maps of increasing complexity. Our methodology produces a significant boost in the discounted return achieved by the agent, even in the first batches of training. Moreover, inductive learning does not compromise the computational time required by Q-learning and learned rules quickly converge to an explanation of the agent policy.