Roland Hafner

Imagined Value Gradients: Model-Based Policy Optimization with Transferable Latent Dynamics Models

2019 · arXiv (Cornell University)

Humans are masters at quickly learning many complex tasks, relying on an approximate understanding of the dynamics of their environments. In much the same way, we would like our learning agents to quickly adapt to …

Less is more -- the Dispatcher/ Executor principle for multi-task Reinforcement Learning

2023 · arXiv (Cornell University)

Humans instinctively know how to neglect details when it comes to solve complex decision making problems in environments with unforeseeable variations. This abstraction process seems to be a vital property for most biological systems and …