conftrace_

nonstationary episodic mdp

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

state marginal distribution (1) marginalized importance sampling (1) markov decision process (1) off-policy evaluation (1) reinforcement learning (1)

Papers

Towards Optimal Off-Policy Evaluation for Reinforcement Learning with Marginalized Importance Sampling NeurIPS 2019