Look where you look! Saliency-guided Q-networks for visual RL tasks. (arXiv:2209.09203v2 [cs.LG] UPDATED)

Deep reinforcement learning policies, despite their outstanding efficiency in
simulated visual control tasks, have shown disappointing ability to generalize
across disturbances in the input training images. Changes in image statistics
or distracting background elements are pitfalls that prevent generalization and
real-world applicability of such control policies. We elaborate on the
intuition that a good visual policy should be able to identify which pixels are
important for its decision, and preserve this identification of important
sources of information across images. This …

arxiv networks