MEGA-DAgger: Imitation Learning with Multiple Imperfect Experts
Imitation learning has been widely applied to various autonomous systems thanks to recent development in interactive algorithms that address covariate shift and compounding errors induced by traditional approaches like behavior cloning. However, existing interactive imitation learning methods assume access to one perfect expert. Whereas in reality, it is more likely to have multiple imperfect experts instead. In this paper, we propose MEGA-DAgger, a new DAgger variant that is suitable for interactive learning with multiple imperfect experts. First, unsafe demonstrations are filtered while aggregating the training data, so the imperfect demonstrations have little influence when training the novice policy. Next, experts are evaluated and compared on scenarios-specific metrics to resolve the conflicted labels among experts. Through experiments in autonomous racing scenarios, we demonstrate that policy learned using MEGA-DAgger can outperform both experts and policies learned using the state-of-the-art interactive imitation learning algorithms such as Human-Gated DAgger. The supplementary video can be found at \url{https://youtu.be/wPCht31MHrw}.
Code (1)
Tasks
Autonomous RacingImitation LearningSimilar Papers 제목 키워드 기반
A Note on Sample Complexity of Interactive Imitation Learning with Log Loss
Imitation learning (IL) is a general paradigm for learning from experts in sequential decision-making problems. Recent advancements in IL have shown that offline imitation learning, specifically Behavior Cloning (BC) wit…
Decision MakingImitation LearningSequential Decision MakingOperator Learning with Gaussian Processes
Operator learning focuses on approximating mappings $\mathcal{G}^\dagger:\mathcal{U} \rightarrow\mathcal{V}$ between infinite-dimensional spaces of functions, such as $u: \Omega_u\rightarrow\mathbb{R}$ and $v: \Omega_v\r…
Gaussian ProcessesOperator learningRLIF: Interactive Imitation Learning as Reinforcement Learning
Although reinforcement learning methods offer a powerful framework for automatic skill acquisition, for practical learning-based control problems in domains such as robotics, imitation learning often provides a more conv…
continuous-controlContinuous ControlImitation Learningreinforcement-learning+1IALE: Imitating Active Learner Ensembles
Active learning (AL) prioritizes the labeling of the most informative data samples. However, the performance of AL heuristics depends on the structure of the underlying classifier model and the data. We propose an imitat…
Active LearningImitation LearningLazyDAgger: Reducing Context Switching in Interactive Imitation Learning
Corrective interventions while a robot is learning to automate a task provide an intuitive method for a human supervisor to assist the robot and convey information about desired behavior. However, these interventions can…
continuous-controlContinuous ControlImitation Learning