Prioritized Soft Q-Decomposition for Lexicographic Reinforcement Learning

Finn Rietz, Erik Schaffernicht, Stefan Heinrich, J. A. Stork
2/12/2026

No official code found. Best implementation: frietz58/psqd (4 stars, last commit 2024-03-14).

Semantic Scholar

Code Implementations(1)

frietz58/psqdCommunity58%

Source code for paper "Prioritized Soft Q-Decomposition for Lexicographic Reinforcement Learning"

41PythonJun 9, 20232 years ago
constrained-reinforcement-learningdeep-neural-networksreinforcement-learning

Cite this paper

@article{rietz2026prioritized,
  title  = {Prioritized Soft Q-Decomposition for Lexicographic Reinforcement Learning},
  author = {Finn Rietz and Erik Schaffernicht and Stefan Heinrich and J. A. Stork},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:e90e58367fc6f7bc4cefd3b470304ad84d7fcfba},
  journal = {ICLR 2024 2024}
}

Discussion