Scholar
Martin Tappler
Google Scholar ID: PoUtPGQAAAAJ
TU Wien
Citations & Impact
Citations
846
H-index
17
i10-index
26
Publications
20
Co-authors
13
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Paper 'Rule-Guided Reinforcement Learning Policy Evaluation and Improvement' accepted at IJCAI 2025.
- Paper 'Test Where Decisions Matter: Importance-driven Testing for Deep Reinforcement Learning' accepted at NeurIPS 2024.
- Won the TAYSIR competition with the theme 'TRANSFORMERS+RNN: ALGORITHMS TO YIELD SIMPLE AND INTERPRETABLE REPRESENTATIONS'.
- Developed a learning-based testing approach for RL agents to be presented at ICST 2024.
- Proposed a method to repair deep reinforcement learning policies from fuzz-testing data to be introduced at ICSE 2024.
- Paper 'Search-Based Testing of Reinforcement Learning' accepted at IJCAI 2022.
Research Experience
- Participates in the TAIGER project within the TrustCPS group; research includes rule-guided reinforcement learning policy evaluation and improvement, importance-driven testing for deep reinforcement learning, etc.
Education
- Specific educational background details are not provided.
Background
- Martin Tappler is a Postdoc at TU Wien, focusing on explainable reinforcement learning, runtime verification, and understanding machine learning.
Miscellany
- No personal interests or other relevant information provided.
