activity
20172022
most citedIntelligent problem-solving as integrated hierarchical reinforcement learning

93 citations · 95 across the 4 of their papers we have counts for

collaborators

8 papers

cs.AI2022★ 93 cited

Intelligent problem-solving as integrated hierarchical reinforcement learning

Manfred Eppe, Christian Gumbsch, Matthias Kerzel +3

According to cognitive psychology and related disciplines, the development of complex problem-solving behaviour in biological agents depends on hierarchical cognitive mechanisms. H…

cs.AI2020

Hierarchical principles of embodied reinforcement learning: A review

Manfred Eppe, Christian Gumbsch, Matthias Kerzel +3

Cognitive Psychology and related disciplines have identified several critical mechanisms that enable intelligent biological agents to learn to solve complex problems. There exists…

cs.RO2020★ 1 cited

Robotic self-representation improves manipulation skills and transfer learning

Phuong D. H. Nguyen, Manfred Eppe, Stefan Wermter

Cognitive science suggests that the self-representation is critical for learning and problem-solving. However, there is a lack of computational methods that relate this claim to co…

cs.RO2020★ 1 cited

Reinforcement Learning with Time-dependent Goals for Robotic Musicians

Thilo Fryen, Manfred Eppe, Phuong D. H. Nguyen +2

Reinforcement learning is a promising method to accomplish robotic control tasks. The task of playing musical instruments is, however, largely unexplored because it involves the ch…

cs.RO2020

Sensorimotor representation learning for an "active self" in robots: A model survey

Phuong D. H. Nguyen, Yasmin Kim Georgie, Ezgi Kayhan +3

Safe human-robot interactions require robots to be able to learn how to behave appropriately in \sout{humans' world} \rev{spaces populated by people} and thus to cope with the chal…

cs.LG2020

Curious Hierarchical Actor-Critic Reinforcement Learning

Frank Röder, Manfred Eppe, Phuong D. H. Nguyen +1

Hierarchical abstraction and curiosity-driven exploration are two common paradigms in current reinforcement learning approaches to break down difficult problems into a sequence of…