POLTER: Policy Trajectory Ensemble Regularization for Unsupervised Reinforcement Learning. (arXiv:2205.11357v2 [cs.LG] UPDATED)

The goal of Unsupervised Reinforcement Learning (URL) is to find a
reward-agnostic prior policy on a task domain, such that the sample-efficiency
on supervised downstream tasks is improved. Although agents initialized with
such a prior policy can achieve a significantly higher reward with fewer
samples when finetuned on the downstream task, it is still an open question how
an optimal pretrained prior policy can be achieved in practice. In this work,
we present POLTER (Policy Trajectory Ensemble Regularization) - a …

arxiv ensemble policy regularization reinforcement reinforcement learning unsupervised