paper-with-me

홈 › Papers

Variational Imitation Learning with Diverse-quality Demonstrations

2020-01-01 · ICML 2020 1 · Voot Tangkaratt, Bo Han, Mohammad Emtiyaz Khan, Masashi Sugiyama

Learning from demonstrations can be challenging when the quality of demonstrations is diverse, and even more so when the quality is unknown and there is no additional information to estimate the quality. We propose a new method for imitation learning in such scenarios. We show that simple quality-estimation approaches might fail due to compounding error, and fix this issue by jointly estimating both the quality and reward using a variational approach. Our method is easy to implement within reinforcement-learning frameworks and also achieves state-of-the-art performance on continuous-control benchmarks.Our work enables scalable and data-efficient imitation learning under more realistic settings than before.

📄 PDF Abstract BibTeX

Code (1)

voot-t/vild_code 공식 구현 pytorch

Tasks

continuous-controlContinuous ControlImitation Learningreinforcement-learningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

VILD: Variational Imitation Learning with Diverse-quality Demonstrations

2019-09-15 · Voot Tangkaratt, Bo Han, Mohammad Emtiyaz Khan, Masashi Sugiyama

The goal of imitation learning (IL) is to learn a good policy from high-quality demonstrations. However, the quality of demonstrations in reality can be diverse, since it is easier and cheaper to collect demonstrations f…

continuous-controlContinuous ControlImitation LearningReinforcement Learning

Robust Imitation of Diverse Behaviors

2017-07-10 · NeurIPS 2017 12 · Ziyu Wang, Josh Merel, Scott Reed, Greg Wayne 외

Deep generative models have recently shown great promise in imitation learning for motor control. Given enough data, even supervised approaches can do one-shot imitation learning; however, they are vulnerable to cascadin…

Imitation LearningMuJoCo

Robust Offline Imitation Learning from Diverse Auxiliary Data

2024-10-04 · Udita Ghosh, Dripta S. Raychaudhuri, Jiachen Li, Konstantinos Karydis 외

Offline imitation learning enables learning a policy solely from a set of expert demonstrations, without any environment interaction. To alleviate the issue of distribution shift arising due to the small amount of expert…

Imitation Learning

Trajectory VAE for multi-modal imitation

2019-05-01 · ICLR 2019 5 · Xiaoyu Lu, Jan Stuehmer, Katja Hofmann

We address the problem of imitating multi-modal expert demonstrations in sequential decision making problems. In many practical applications, for example video games, behavioural demonstrations are readily available that…

continuous-controlContinuous ControlDecision MakingImitation Learning+2

Imitation from Diverse Behaviors: Wasserstein Quality Diversity Imitation Learning with Single-Step Archive Exploration

2024-11-11 · Xingrui Yu, Zhenglin Wan, David Mark Bossens, Yueming Lyu 외

Learning diverse and high-performance behaviors from a limited set of demonstrations is a grand challenge. Traditional imitation learning methods usually fail in this task because most of them are designed to learn one s…

continuous-controlContinuous ControlDiversityImitation Learning+1