Christopher Thierauf, PhD

Tag: Neurosymbolic

Integrations between symbolic systems, like DYNOS-R or DIARC, and machine learning policies.

In Other

A Gentle Introduction to Symbolic Planning and Reasoning

Tagged Autonomy, DYNOS, Neurosymbolic

Symbolic planning, decision making, and logics made simple(r).
(more…)

December 2, 2025
In Publications

Robots that Learn to Solve Symbolic Novelties with Self-Generated RL Simulations.

Tagged Neurosymbolic, Reinforcement Learning

Christopher Thierauf, Matthias Scheutz. International Conference on Development and Learning (ICDL) 2025.

We solve hard problems by imagining different outcomes in our head. How can robots do the same?
(more…)

September 27, 2025
In Publications

Fixing Symbolic Plans with Reinforcement Learning in Object-Based Action Spaces.

Tagged Neurosymbolic, Reinforcement Learning, Resilience

Christopher Thierauf, Matthias Scheutz. IEEE IROS 2024.

We can redesign the typical reinforcement learning pipeline to train faster and integrate with symbolic plans by training on the environment directly, not the robot within it.

You can read the paper here.
(more…)

October 14, 2024