AMLGym: benchmarking action model learning

Framework for experimenting with action model learning approaches and evaluating the learned domain models.

Installation

pip install amlgym

Example usage

from amlgym.algorithms import get_algorithm
agent = get_algorithm('OffLAM')
model = agent.learn('path/to/domain.pddl', ['path/to/trace0', 'path/to/trace1'])
print(model)

Documentation

Tutorials and API documentation is accessible on Read the Docs

State-of-the-art Algorithms

AMLGym provides seamless integration with state-of-the-art algorithms for offline learning classical planning domains from an input set of trajectories in the following settings:

full observability: SAM [1].
partial observability: OffLAM [2].
full and noisy observability: NOLAM [3], ROSAME [4].

[1] "Safe Learning of Lifted Action Models", B. Juba and H. S. Le, and R. Stern, Proceedings of the 18th International Conference on Principles of Knowledge Representation and Reasoning, 2021.

[2] "Lifted Action Models Learning from Partial Traces", L. Lamanna, L. Serafini, A. Saetti, A. Gerevini, and P. Traverso, Artificial Intelligence Journal, 2025.

[3] "Action Model Learning from Noisy Traces: a Probabilistic Approach", L. Lamanna and L. Serafini, Proceedings of the Thirty-Fourth International Conference on Automated Planning and Scheduling, 2024.

[4] "Neuro-symbolic learning of lifted action models from visual traces", X. Kai, S. Gould, and S. Thiébaux, Proceedings of the Thirty-Fourth International Conference on Automated Planning and Scheduling, 2024.

Adding an algorithm

PRs with new or existing state-of-the-art algorithms are welcome:

Add the algorithm PyPI package in requirements.txt
Create a Python class in algorithms which inherits from AlgorithmAdapter.py and implements the learn method

Evaluation

AMLGym can evaluate a PDDL model by means of several metrics:

Syntactic similarity
Problem solving
Predicted applicability and predicted effects

Benchmarking

See the benchmark package for details.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Citing

Not yet available

Metadata

Release files for amlgym 1.0.13

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for amlgym 1.0.13
File	Size	Uploaded
amlgym-1.0.13.tar.gz	2.4 MB	Oct 13, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for amlgym 1.0.13
File	Interpreter	ABI	Platform	Reset
amlgym-1.0.13-py3-none-any.whl 4.3 MB Oct 13, 2026	Python 3	none	any	Details

Total release size: 6.7 MB

Release files / amlgym-1.0.13.tar.gz

Download URL	amlgym-1.0.13.tar.gz
Size	2.4 MB
Tags	Source
SHA-256 checksum How to use checksums	`48a72a1c80f5c7bea69b9240fff0fe58e0bf4b8231a544737041071a256851ec`
BLAKE2b-256 checksum How to use checksums	`0f743d1c20b2622d0e3e99cc5ef280c6984bf8820c2f3f64d206f518f4e5bcfe`
Upload date	Oct 13, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.2.0 CPython/3.10.13`

Release files / amlgym-1.0.13-py3-none-any.whl

Download URL	amlgym-1.0.13-py3-none-any.whl
Size	4.3 MB
Tags	Python 3
SHA-256 checksum How to use checksums	`8eb9df343990d68560d8319dbb5557a59a7c13339de1cd433c2d054851b37ee0`
BLAKE2b-256 checksum How to use checksums	`ed38f197f6af3d5d9b8e47d09fbb8670d6f07564d08296942588f722f9299ec9`
Upload date	Oct 13, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.2.0 CPython/3.10.13`