NASGym: A simple OpenAI Gym environment for Neural Architecture Search (NAS). This is a python package developed for the research project Learning to reinforcement learn for Neural Architecture Search. The environment is fully compatible with the OpenAI baselines. It implements the RL steps for NAS, using the Neural Structure Code (NSC) of BlockQNN: Efficient Block-wise Neural Network Architecture Generation to encode the networks and make architectural changes. Under this setting, a Neural Network (i.e. the state for the reinforcement learning agent) is modeled as a list of NSCs, an action is the addition of a layer to the network, and the reward is the accuracy after the early-stop training. The datasets considered so far are the CIFAR-10 dataset (default) and the meta-dataset (it has to be downloaded as specified in the original repository).

Keywords for this software

Anything in here will be replaced on browsers that support the canvas element

References in zbMATH (referenced in 1 article )

Showing result 1 of 1.
Sorted by year (citations)

  1. Aebel Joe Shibu, Sadhana S, Shilpa N, Pratyush Kumar: VeRLPy: Python Library for Verification of Digital Designs with Reinforcement Learning (2021) arXiv