Model-Based Inverse Reinforcement Learning from Visual Demonstrations
Model-Based Inverse Reinforcement Learning from Visual Demonstrations
复制标题
基于模型的视觉演示逆强化学习
DOI:
--
复制
发表时间:
2020
期刊:
影响因子:
--
通讯作者:
Franziska Meier
中科院分区:
文献类型:
--
作者:
Neha Das;Sarah Bechtle;Todor Davchev;Dinesh Jayaraman;Akshara Rai;Franziska Meier
Scaling model-based inverse reinforcement learning (IRL) to real robotic manipulation tasks with unknown dynamics remains an open problem. The key challenges lie in learning good dynamics models, developing algorithms that scale to high-dimensional state-spaces and being able to learn from both visual and proprioceptive demonstrations. In this work, we present a gradient-based inverse reinforcement learning framework that utilizes a pre-trained visual dynamics model to learn cost functions when given only visual human demonstrations. The learned cost functions are then used to reproduce the demonstrated behavior via visual model predictive control. We evaluate our framework on hardware on two basic object manipulation tasks.
DOI:
10.1109/icpr48806.2021.9412010
发表时间:
2019-06
期刊:
2020 25th International Conference on Pattern Recognition (ICPR)
影响因子:
--
作者:
Yevgen Chebotar;Artem Molchanov;Sarah Bechtle;L. Righetti;Franziska Meier;G. Sukhatme
通讯作者:
Yevgen Chebotar;Artem Molchanov;Sarah Bechtle;L. Righetti;Franziska Meier;G. Sukhatme