Hierarchical Reinforcement Learning with Timed Subgoals

Authors: Nico Gürtler, Dieter Büchler, Georg Martius

NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our experiments on a range of standard benchmarks and three new challenging dynamic reinforcement learning environments show that our method is capable of sample-efficient learning where an existing state-of-the-art subgoal-based HRL method fails to learn stable solutions.
Researcher Affiliation Academia Max Planck Institute for Intelligent Systems Tübingen, Germany {nguertler, dbuechler, gmartius}@tue.mpg.de
Pseudocode No The paper describes the algorithm steps in text but does not include a formally labeled pseudocode block or algorithm figure.
Open Source Code Yes Videos and code, including our algorithm and the proposed dynamic environments, can be found at https://github.com/martius-lab/Hi TS.
Open Datasets Yes The environments comply with Open AI s gym interface and are available at https://github.com/martius-lab/Hi TS.
Dataset Splits No The paper discusses training and evaluates on benchmarks but does not explicitly provide specific percentages or counts for training, validation, or test dataset splits.
Hardware Specification No No specific hardware details such as GPU/CPU models, memory, or cloud instance types used for running experiments were mentioned in the paper.
Software Dependencies No The paper mentions software components like Soft Actor-Critic (SAC) and OpenAI Gym but does not provide specific version numbers for these or other software dependencies.
Experiment Setup No The paper states that 'Details about training and hyperparameter optimization are given in Suppl. C.' but these specific details are not provided within the main text.