conftrace_

discounted return

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

state-action pair (1) discounted reward (1) stationary distribution (1) value function (1) importance sampling (1) off-policy evaluation (1) reinforcement learning (1)

Papers

DualDICE: Behavior-Agnostic Estimation of Discounted Stationary Distribution Corrections NeurIPS 2019