The identification of pathways leading to robust mitigation of dangerous anthropogenic climate change is nowadays of particular interest not only to the scientific community but also to policy makers and the wider public. Increasingly complex, non-linear World-Earth system models are used for describing the dynamics of the biophysical Earth system and the socio-economic and socio-cultural World of human societies and their interactions.
In this talk, I want to present our framework in which we propose to combine recently developed machine learning techniques, namely deep reinforcement learning (DRL), with classical analysis of trajectories in the World-Earth system as an approach to extend the field of Earth system analysis by a new method. Based on the concept of the agent-environment interface, I present our newly developed method for using a DRL-agent that is able to act and learn in variable manageable environment models of the Earth system in order to discover management strategies for sustainable development. I will show that the agent is able to learn novel, previously undiscovered policies that navigate the system into sustainable regions of the underlying conceptual models of the World-Earth system.