# Safe Learning of PDDL Domains with Conditional Effects -- Extended Version

arXiv: https://arxiv.org/abs/2403.15251 · HTML: https://mlsanity.com/paper/2403.15251/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 35 references that are in the map.
- First posted on arXiv 22 Mar 2024.

## Builds on (most cited first, 5 of 5)

- [Safe Reinforcement Learning in Constrained Markov Decision Processes](https://mlsanity.com/paper/2008.06626/) (2020)
- [Efficient, Safe, and Probably Approximately Complete Learning of Action Models](https://mlsanity.com/paper/1705.08961/) (2017)
- [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)
- [Learning STRIPS Action Models with Classical Planning](https://mlsanity.com/paper/1903.01153/) (2019)

## Built on by (most cited first, 2 of 2)

- [Using large language models for embodied planning introduces systematic safety risks](https://mlsanity.com/paper/2604.18463/) (2026)
- [When to ASK: Uncertainty-Gated Language Assistance for Reinforcement Learning](https://mlsanity.com/paper/2604.02226/) (2026)

## Abstract (arXiv)

Powerful domain-independent planners have been developed to solve various types of planning problems. These planners often require a model of the acting agent's actions, given in some planning domain description language. Manually designing such an action model is a notoriously challenging task. An alternative is to automatically learn action models from observation. Such an action model is called safe if every plan created with it is consistent with the real, unknown action model. Algorithms for learning such safe action models exist, yet they cannot handle domains with conditional or universal effects, which are common constructs in many planning problems. We prove that learning non-trivial safe action models with conditional effects may require an exponential number of samples. Then, we identify reasonable assumptions under which such learning is tractable and propose SAM Learning of Conditional Effects (Conditional-SAM), the first algorithm capable of doing so. We analyze Conditional-SAM theoretically and evaluate it experimentally. Our results show that the action models learned by Conditional-SAM can be used to solve perfectly most of the test set problems in most of the experimented domains.