Skip to content
conftrace_

surprise minimizing reinforcement learning

1 paper

Explore in graph

Also known as

SMIRL

Co-occurring keywords · papers mentioning both

task reward (1) bipedal robot (1) unsupervised reinforcement learning (1) density models (1)

Papers

SMiRL: Surprise Minimizing Reinforcement Learning in Unstable Environments ICLR 2021