DAC: The Double Actor-Critic Architecture for Learning Options

Authors: Shangtong Zhang, Shimon Whiteson

NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We conduct an empirical study on challenging robot simulation tasks.
Researcher Affiliation Academia Shangtong Zhang, Shimon Whiteson Department of Computer Science University of Oxford {shangtong.zhang, shimon.whiteson}@cs.ox.ac.uk
Pseudocode Yes The pseudocode of DAC is provided in the supplementary materials.
Open Source Code Yes All implementations are made publicly available 1. https://github.com/ShangtongZhang/DeepRL
Open Datasets Yes We consider four robot simulation tasks used by Smith et al. (2018) from Open AI gym (Brockman et al., 2016). ... We use 6 pairs of tasks from Deep Mind Control Suite (DMControl, Tassa et al. 2018)
Dataset Splits No The paper does not provide specific training/validation/test dataset splits. It uses reinforcement learning environments (OpenAI Gym, DeepMind Control Suite) where data is generated through interaction.
Hardware Specification No The Acknowledgments section mentions 'a generous equipment grant from NVIDIA' but does not specify the exact GPU models, CPU models, or other hardware specifications used for experiments.
Software Dependencies No The paper mentions using PPO, A2C, OpenAI Gym, and DeepMind Control Suite, but does not provide specific version numbers for these software dependencies or any other libraries.
Experiment Setup Yes Our PPO implementation uses the same architecture and hyperparameters reported by Schulman et al. (2017). ... We use 4 options for all algorithms, following Smith et al. (2018). We report the online training episode return, smoothed by a sliding window of size 20.