Learning Task-relevant Representations for Generalization via Characteristic Functions of Reward Sequence Distributions. (arXiv:2205.10218v1 [cs.LG])

Generalization across different environments with the same tasks is critical
for successful applications of visual reinforcement learning (RL) in real
scenarios. However, visual distractions -- which are common in real scenes --
from high-dimensional observations can be hurtful to the learned
representations in visual RL, thus degrading the performance of generalization.
To tackle this problem, we propose a novel approach, namely Characteristic
Reward Sequence Prediction (CRESP), to extract the task-relevant information by
learning reward sequence distributions (RSDs), as the reward …

arxiv learning