gym-saturation: Gymnasium Environments for Saturation Provers (System description)-Reference-Cited by-同舟云学术

gym-saturation: Gymnasium Environments for Saturation Provers (System description)

Published:2023 Issue: Volume: Page:187-199
ISSN:0302-9743
Container-title:Lecture Notes in Computer Science
language:
Short-container-title:

Author:

Shminke Boris^ORCID

Abstract

AbstractThis work describes a new version of a previously published Python package — : a collection of OpenAI Gym environments for guiding saturation-style provers based on the given clause algorithm with reinforcement learning. We contribute usage examples with two different provers: Vampire and iProver. We also have decoupled the proof state representation from reinforcement learning per se and provided examples of using a known Python code embedding model as a first-order logic representation. In addition, we demonstrate how environment wrappers can transform a prover into a problem similar to a multi-armed bandit. We applied two reinforcement learning algorithms (Thompson sampling and Proximal policy optimisation) implemented in Ray RLlib to show the ease of experimentation with the new release of our package.

Publisher

Springer Nature Switzerland

Link

https://link.springer.com/content/pdf/10.1007/978-3-031-43513-3_11

Reference37 articles.

1. Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous systems (2015). https://www.tensorflow.org/. Software available from tensorflow.org

2. Abdelaziz, I., et al.: Learning to guide a saturation-based theorem prover. IEEE Trans. Pattern Anal. Mach. Intell. 45(1), 738–751 (2023). https://doi.org/10.1109/TPAMI.2022.3140382

3. Agrawal, S., Goyal, N.: Thompson sampling for contextual bandits with linear payoffs. In: Dasgupta, S., McAllester, D. (eds.) Proceedings of the 30th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 28, pp. 127–135. PMLR, Atlanta, Georgia, USA (17–19 Jun 2013). https://proceedings.mlr.press/v28/agrawal13.html

4. Alon, U., Zilberstein, M., Levy, O., Yahav, E.: Code2Vec: learning distributed representations of code. Proceed. ACM Programm. Lang. 3(POPL), 1–29 (2019). https://doi.org/10.1145/3290353

5. Ballout, A., da Costa Pereira, C., Tettamanzi, A.G.B.: Learning to classify logical formulas based on their semantic similarity. In: Aydoğan, R., Criado, N., Lang, J., Sanchez-Anguix, V., Serramia, M. (eds.) PRIMA 2022: Principles and Practice of Multi-Agent Systems, pp. 364–380. PRIMA 2022. LNCS, vol. 13753. Springer, Cham (2023). https://doi.org/10.1007/978-3-031-21203-1_22