Sequential Counterfactual Decision-Making Under Confounded Reward

06/05/2022
by   Erik Skalnes, et al.
0

We investigate the limitations of random trials when the cause of interest is confounded with the effect by formalizing a counterfactual policy-space where the agent's natural predilection is input to a soft-intervention.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset
Success!
Error Icon An error occurred

Sign in with Google

×

Use your Google Account to sign in to DeepAI

×

Consider DeepAI Pro