CORL (Causal discovery with Ordering-based Reinforcement Learning) (Q6482957)
From MaRDI portal
A reinforcement learning approach to DAG learning by treatening a vertex order problem as a multi-step Markov decision process, implement the ordering generating process with an encoder-decoder architecture, and finally use RL to optimize the proposed model based on the reward mechanisms designed for each ordering
- CORL
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | CORL (Causal discovery with Ordering-based Reinforcement Learning) |
A reinforcement learning approach to DAG learning by treatening a vertex order problem as a multi-step Markov decision process, implement the ordering generating process with an encoder-decoder architecture, and finally use RL to optimize the proposed model based on the reward mechanisms designed for each ordering |
|
