Task-Relevant Adversarial Imitation Learning
We show that a critical vulnerability in adversarial imitation is the tendency of discriminator networks to learn spurious associations between visual features and expert labels. When the discriminator focuses on task-irrelevant features, it does not provide an informative reward signal, leading to poor task performance. We analyze this problem in detail and propose a solution that outperforms standard Generative Adversarial Imitation Learning (GAIL). Our proposed method, Task-Relevant Adversarial Imitation Learning (TRAIL), uses constrained discriminator optimization to learn informative rewards. In comprehensive experiments, we show that TRAIL can solve challenging robotic manipulation tasks from pixels by imitating human operators without access to any task rewards, and clearly outperforms comparable baseline imitation agents, including those trained via behaviour cloning and conventional GAIL.
Code (0)
등록된 구현이 없습니다.
Tasks
Imitation LearningSimilar Papers 제목 키워드 기반
SeMAIL: Eliminating Distractors in Visual Imitation via Separated Models
Model-based imitation learning (MBIL) is a popular reinforcement learning method that improves sample efficiency on high-dimension input sources, such as images and videos. Following the convention of MBIL research, exis…
Imitation LearningTask-Centric Policy Optimization from Misaligned Motion Priors
Humanoid control often leverages motion priors from human demonstrations to encourage natural behaviors. However, such demonstrations are frequently suboptimal or misaligned with robotic tasks due to embodiment differenc…
Reinforcement LearningLatent Policies for Adversarial Imitation Learning
This paper considers learning robot locomotion and manipulation tasks from expert demonstrations. Generative adversarial imitation learning (GAIL) trains a discriminator that distinguishes expert from agent transitions, …
DecoderImitation LearningLearn what matters: cross-domain imitation learning with task-relevant embeddings
We study how an autonomous agent learns to perform a task from demonstrations in a different domain, such as a different environment or different agent. Such cross-domain imitation learning is required to, for example, t…
Imitation LearningFre-CW: Targeted Attack on Time Series Forecasting using Frequency Domain Loss
Transformer-based models have made significant progress in time series forecasting. However, a key limitation of deep learning models is their susceptibility to adversarial attacks, which has not been studied enough in t…
Time Series ForecastingTime Series PredictionAdversarial Robustness