ConceptCausal Reinforcement Learning / CRL
Causal Reinforcement Learning
A methodology that combines causal inference with reinforcement learning. By learning a structural causal model (SCM) of the environment, agents can reason about interventions and counterfactuals, thereby improving the robustness and generalization of policies.
Timeline (last 90 days)
Sep 11
The common bottleneck of existing causal reinforcement learning methods is the acquisition of causal structure, which either needs to be learned from data (error-prone) or manually specified by experts (costly).
Unverified50%