conftrace_

trimmed mean estimation

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

heavy-tailed reward distribution (1) trimmed mean (1) heavy-tailed reward (1) robust mean estimation (1) pessimistic value iteration (1) data corruption (1) robust estimation (1) offline reinforcement learning (1)

Papers

Exact Policy Recovery in Offline RL with Both Heavy-Tailed Rewards and Data Corruption AAAI 2024