Model-free reinforcement learning aims to offer off-the-shelf solutions for controlling dynamical systems without requiring models of the system dynamics.

Recently, the Deep Learning community has become interested in evolutionary optimization (EO) as a means to address hard optimization problems, e.g.

Model-free reinforcement learning aims to offer off-the-shelf solutions for controlling dynamical systems without requiring models of the system dynamics.

A promising alternative to the computationally expensive Neural Architecture Search (NAS) involves the development of Zero Cost Proxies (ZCPs), which correlate well with trained performance, but can be computed through a single forward/backward pass on a randomly sampled batch of data. In this paper, we investigate the effectiveness of ZCPs for HAR on six benchmark datasets, and demonstrate that they discover network architectures that obtain within 5% of performance attained by full-scale training involving 1500 randomly sampled architectures. This results in substantial computational savings as high-performing architectures can be discovered with minimal training. Our experiments not only introduce ZCPs to sensor-based HAR, but also demonstrate that they are robust to data noise, further showcasing their suitability for practical scenarios.

HOOF is robust to settings within this range. We could not present results for Ant and Walker due to space constraints. Thus we are restricted to zero order optimisers. For natural gradients like TNPG, HOOF does not add any new hyperparameters beyond those used by grid search - i.e. Other methods like PBT introduce more hyperparameters than these.

We will include these statements in the revised paper.

Hyperparameter optimization is crucial for obtaining peak performance of machine learning models.

This appendix contains additional material for the paper "Optimistic tree search

Adversarial attacks based on randomized search schemes have obtained state-of-the-art results in black-box robustness evaluation recently.