most citedDeep reinforcement learning uncovers processes for separating azeotropic mixtures without prior knowledge

1 citations · 1 across the 1 of their papers we have counts for

collaborators
Showing cs.LGShow all

2 papers · 1 filter

cs.LG2023★ 1 cited

Deep reinforcement learning uncovers processes for separating azeotropic mixtures without prior knowledge

Quirin Göttl, Jonathan Pirnay, Jakob Burger +1

Process synthesis in chemical engineering is a complex planning problem due to vast search spaces, continuous parameters and the need for generalization. Deep reinforcement learnin…

cs.LG2023★ 2 cited

Policy-Based Self-Competition for Planning Problems

Jonathan Pirnay, Quirin Göttl, Jakob Burger +1

AlphaZero-type algorithms may stop improving on single-player tasks in case the value network guiding the tree search is unable to approximate the outcome of an episode sufficientl…