SFP: State-free Priors for Exploration in Off-Policy Reinforcement Learning. (arXiv:2205.13528v3 [cs.LG] UPDATED)

Efficient exploration is a crucial challenge in deep reinforcement learning.
Several methods, such as behavioral priors, are able to leverage offline data
in order to efficiently accelerate reinforcement learning on complex tasks.
However, if the task at hand deviates excessively from the demonstrated task,
the effectiveness of such methods is limited. In our work, we propose to learn
features from offline data that are shared by a more diverse range of tasks,
such as correlation between actions and directedness. Therefore, …

arxiv exploration free learning policy reinforcement reinforcement learning state