POLY-HOOT: Monte-Carlo Planning in Continuous Space MDPs with Non-Asymptotic Analysis

Authors: Weichao Mao, Kaiqing Zhang, Qiaomin Xie, Tamer Basar

NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We further provide experimental results that corroborate our theoretical findings.
Researcher Affiliation Academia Weichao Mao ECE and CSL University of Illinois at Urbana-Champaign weichao2@illinois.edu Kaiqing Zhang ECE and CSL University of Illinois at Urbana-Champaign kzhang66@illinois.edu Qiaomin Xie ORIE Cornell University qiaomin.xie@cornell.edu Tamer Ba sar ECE and CSL University of Illinois at Urbana-Champaign basar1@illinois.edu
Pseudocode Yes Our algorithm for continuous space MCTS, Polynomial Hierarchical Optimistic Optimization applied to Trees (POLY-HOOT), is presented in Algorithm 1.
Open Source Code No The paper does not provide a link to open-source code for the described methodology or state that it is available.
Open Datasets Yes We have chosen three benchmark tasks from Open AI Gym (Open AI, 2016)
Dataset Splits No The paper does not explicitly provide details about training, validation, or test splits. For the control tasks, performance is averaged over runs rather than using predefined dataset splits.
Hardware Specification Yes All tests are averaged over 10 (new) runs on a laptop with an Intel Core i5-9300H CPU.
Software Dependencies No The paper mentions 'Open AI Gym (Open AI, 2016)' but does not provide specific version numbers for this or any other software dependencies.
Experiment Setup No The paper states that 'The detailed experiment settings as well as additional experiment results can be found in Appendix E.' but these details are not present in the provided text.