Official repository for the paper "DeepDFA: Automata Learning through Neural Probabilistic Relaxations". Elena Umili and Roberto Capobianco. ECAI 2024.

This is the code repository accompanying the ICML 2021 paper LTL2Action: Generalizing LTL Instructions for Multi-Task RL (https://arxiv.org/abs/2102.06858).

Benchmarks for the Trace Alignment repository

Declarative Trace Alignment via Automated Planning

Automaton generation

Code for paper Lang2LTL: Grounding Complex Natural Language Commands for Temporal Tasks in Unseen Environments

Paper collections of methods that using language to interact with environment, including interact with real world, simulated world or WWW(🏄).

Natural Language (NL) to Linear Temporal Logic (LTL)

FOND4LTLf translates an LTLf/PLTLf-FOND to standard FOND planning problems

Repository containing all implementations and experiments for the EDBN model.

Official implementation of Teaching Temporal Logics to Neural Networks (https://arxiv.org/abs/2003.04218)

Paired Open-Ended Trailblazer (POET) and Enhanced POET

[IROS2020] Encoding formulas as deep networks: Reinforcement learning for zero-shot execution of LTL formulas

implementation of ICML 2018 paper, Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamples

Extracting minimal DFA's from well-trained RNN's

DFA extraction using neural state merging

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

A python tool for solving minDFA problem.

Implementation of PDFAs and PDFA learning algorithm.