Causal Process Models reframe dynamic causal graph discovery as multi-agent reinforcement learning to build sparse time-varying graphs only at active interactions, outperforming dense baselines on physical prediction.
Jake Topping, Francesco Di Giovanni, Benjamin Paul Chamberlain, Xiaowen Dong, and Michael M
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Causal Process Models: Reframing Dynamic Causal Graph Discovery as a Reinforcement Learning Problem
Causal Process Models reframe dynamic causal graph discovery as multi-agent reinforcement learning to build sparse time-varying graphs only at active interactions, outperforming dense baselines on physical prediction.