# Goal Recognition as Reinforcement Learning

arXiv: https://arxiv.org/abs/2202.06356 · HTML: https://mlsanity.com/paper/2202.06356/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 37 references that are in the map.
- First posted on arXiv 13 Feb 2022.

## Builds on (most cited first, 6 of 6)

- [The LAMA Planner: Guiding Cost-Based Anytime Planning with Landmarks](https://mlsanity.com/paper/1401.3839/) (2014)
- [PDDLGym: Gym Environments from PDDL Problems](https://mlsanity.com/paper/2002.06432/) (2020)
- [Understanding the Power and Limitations of Teaching with Imperfect Knowledge](https://mlsanity.com/paper/2003.09712/) (2020)
- [Expected Value of Communication for Planning in Ad Hoc Teamwork](https://mlsanity.com/paper/2103.01171/) (2021)
- [Safe Learning of Lifted Action Models](https://mlsanity.com/paper/2107.04169/) (2021)
- [Learning Partially Observable Deterministic Action Models](https://mlsanity.com/paper/1401.3437/) (2014)

## Built on by (most cited first, 9 of 9)

- [Goal Recognition as a Deep Learning Task: the GRNet Approach](https://mlsanity.com/paper/2210.02377/) (2022)
- [ODGR: Online Dynamic Goal Recognition](https://mlsanity.com/paper/2407.16220/) (2024)
- [GRAIL: Goal Recognition Alignment through Imitation Learning](https://mlsanity.com/paper/2602.14252/) (2026)
- ["Guess what I'm doing": Extending legibility to sequential decision tasks](https://mlsanity.com/paper/2209.09141/) (2022)
- [Goal Recognition via Linear Programming](https://mlsanity.com/paper/2404.07934/) (2024)
- [GRAML: Goal Recognition As Metric Learning](https://mlsanity.com/paper/2505.03941/) (2025)
- [Online Dynamic Goal Recognition in Gym Environments](https://mlsanity.com/paper/2509.23244/) (2025)
- [Online Goal Recognition using Path Signature and Dynamic Time Warping](https://mlsanity.com/paper/2605.07736/) (2026)
- [Multi-Agent Goal Recognition with Team- and Goal-Conditioned Reinforcement Learning and Factorized Branch-and-Bound](https://mlsanity.com/paper/2606.25978/) (2026)

## Abstract (arXiv)

Most approaches for goal recognition rely on specifications of the possible dynamics of the actor in the environment when pursuing a goal. These specifications suffer from two key issues. First, encoding these dynamics requires careful design by a domain expert, which is often not robust to noise at recognition time. Second, existing approaches often need costly real-time computations to reason about the likelihood of each potential goal. In this paper, we develop a framework that combines model-free reinforcement learning and goal recognition to alleviate the need for careful, manual domain design, and the need for costly online executions. This framework consists of two main stages: Offline learning of policies or utility functions for each potential goal, and online inference. We provide a first instance of this framework using tabular Q-learning for the learning stage, as well as three measures that can be used to perform the inference stage. The resulting instantiation achieves state-of-the-art performance against goal recognizers on standard evaluation domains and superior performance in noisy environments.