Interplanetary Trajectory Planning with Monte Carlo Tree Search

Authors: Daniel Hennes, Dario Izzo

IJCAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We discuss our experimental set-up, in particular parameter search and runtime analysis. We evaluate our approach on two well-known missions: Cassini-Huygens and Rosetta.
Researcher Affiliation Academia Daniel Hennes and Dario Izzo European Space Agency Advanced Concepts Team Noordwijk, The Netherlands daniel.hennes@esa.int, dario.izzo@esa.int
Pseudocode No The paper describes the MCTS steps in paragraph text and provides equations, but does not include formal pseudocode or an algorithm block.
Open Source Code No The paper does not provide any explicit statement or link for open-source code for the described methodology.
Open Datasets Yes For this computation we use the analytical planet ephemerides defined by NASA / Jet Propulsion Laboratory1. 1The approximated ephemerides were used as defined in http: //ssd.jpl.nasa.gov/?planet pos [accessed November 2014]
Dataset Splits No The paper describes a parameter search to tune the algorithm's parameters but does not specify training/test/validation dataset splits in the conventional sense for model evaluation.
Hardware Specification No The paper does not provide any specific details about the hardware used for running the experiments.
Software Dependencies No The paper does not list specific software dependencies with version numbers needed to replicate the experiment.
Experiment Setup Yes The UCB-1 (see Equation (1)) and ϵ-greedy (see Equation 2) selection policies require one parameter choice each. We sample 4000 parameter instances uniformly on a logarithmic scale. For each parameter instance, one run of UCT with the selected policy is performed until the computational budget of N Lambert legs is depleted.