This is the original implementation of the COHER approach proposed in: E. Sayar, G. Iacca, A. Knoll, Curriculum learning for robot manipulation tasks with sparse reward through environment shifts, IEEE Access, 2024
To be able to reproduce the results;
cd /code/coher/docker
docker-compose run --rm coher
If you use this repo in your research, please consider citing the paper as follows.
@ARTICLE{10480429,
author={Sayar, Erdi and Iacca, Giovanni and Knoll, Alois},
journal={IEEE Access},
title={Curriculum learning for robot manipulation tasks with sparse reward through environment shifts},
year={2024},
volume={},
number={},
pages={1-1},
keywords={Task analysis;Robots;Heuristic algorithms;Statistics;Sociology;Neural networks;Euclidean distance;Curriculum learning-based reinforcement learning;hindsight experience replay;multi-goal reinforcement learning;robotic control},
doi={10.1109/ACCESS.2024.3382264}}