PALMER: Perception - Action Loop with Memory for Long-Horizon Planning

Authors: Onur Beker, Mohammad Mohammadi, Amir Zamir

NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our experiments are performed in Vi ZDoom [39], Habitat [40], and the Maze2D benchmark [41].
Researcher Affiliation Academia Onur Beker Mohammad Mohammadi Amir Zamir Swiss Federal Institute of Technology (EPFL)
Pseudocode Yes Algorithm 1 R-PRM (Roadmap Construction) and Algorithm 2 R-PRM (Trajectory Restitching Given the Constructed Roadmap)
Open Source Code Yes Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [Yes]
Open Datasets Yes Our experiments are performed in Vi ZDoom [39], Habitat [40], and the Maze2D benchmark [41].
Dataset Splits No The paper mentions "offline training dataset" and "test apartments" but does not specify exact percentages or sample counts for train/validation/test splits.
Hardware Specification No The paper does not explicitly describe the specific hardware used (e.g., GPU/CPU models, memory) to run its experiments in the main text.
Software Dependencies No The paper does not provide specific software dependency details with version numbers.
Experiment Setup Yes dp and c Q are hyperparameters. ... We randomly sample a transition (st, at, st+1) and a time difference T, and set the goal state as sg := st+T , as in hindsight relabelling.