◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Jonas Ehrhardt

2 papers hereh-index 582 citations22 works total

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • first author1
  • middle author1

Across the 2 of 2 papers where every author was matched, so the position is known.

fields
  • cs.AI2

identity via Semantic Scholar / OpenAlex

works on
explainable reinforcement learning 1knowledge-guided exploration 1neuro-symbolic learning 1parametrized action mdp 1sample efficiency 1

From the 1 of 2 linked papers with an AI index.

collaborators
Showing cs.AIShow all

2 papers · 1 filter

cs.AI2026

Knowledge- and Gradient-Guided Reinforcement Learning for Parametrized Action Markov Decision Processes

Jonas Ehrhardt, René Heesch, Oliver Niggemann

The paper introduces KGRL, a reinforcement‑learning method that uses a Datalog knowledge base to filter actions and constrain parameters in Parametrized Action MDPs, and then refin…

cs.AI2024

AAAI Workshop on AI Planning for Cyber-Physical Systems -- CAIPI24

Oliver Niggemann, Gautam Biswas, Alexander Diedrich +3

The workshop 'AI-based Planning for Cyber-Physical Systems', which took place on February 26, 2024, as part of the 38th Annual AAAI Conference on Artificial Intelligence in Vancouv…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.