Showing cs.ROShow all
2 papers · 1 filter
cs.RO2024
Reward Machine Inference for Robotic Manipulation
Mattijs Baert, Sam Leroux, Pieter Simoens
Learning from Demonstrations (LfD) and Reinforcement Learning (RL) have enabled robot agents to accomplish complex tasks. Reward Machines (RMs) enhance RL's capability to train pol…
cs.RO2024
Learning Task Specifications from Demonstrations as Probabilistic Automata
Mattijs Baert, Sam Leroux, Pieter Simoens
Specifying tasks for robotic systems traditionally requires coding expertise, deep domain knowledge, and significant time investment. While learning from demonstration offers a pro…