相关论文: Adversarial Imitation Learning from Visual Observa…

Adversarial methods for imitation learning have been shown to perform well on various control tasks. However, they require a large number of environment interactions for convergence. In this paper, we propose an end-to-end differentiable…

Deep Imitation Learning requires a large number of expert demonstrations, which are not always easy to obtain, especially for complex tasks. A way to overcome this shortage of labels is through data augmentation. However, this cannot be…

Many modern methods for imitation learning and inverse reinforcement learning, such as GAIL or AIRL, are based on an adversarial formulation. These methods apply GANs to match the expert's distribution over states and actions with the…

We consider the problem of using expert data with unobserved confounders for imitation and reinforcement learning. We begin by defining the problem of learning from confounded expert data in a contextual MDP setup. We analyze the…

We study visual domain transfer for end-to-end imitation learning in a realistic and challenging setting where target-domain data are strictly off-policy, expert-free, and scarce. We first provide a theoretical analysis showing that the…

Imitation by observation is an approach for learning from expert demonstrations that lack action information, such as videos. Recent approaches to this problem can be placed into two broad categories: training dynamics models that aim to…

Consider an imitation learning problem that the imitator and the expert have different dynamics models. Most of the current imitation learning methods fail because they focus on imitating actions. We propose a novel state alignment-based…

We consider the problem of imitation learning from a finite set of expert trajectories, without access to reinforcement signals. The classical approach of extracting the expert's reward function via inverse reinforcement learning, followed…

Active learning agents typically employ a query selection algorithm which solely considers the agent's learning objectives. However, this may be insufficient in more realistic human domains. This work uses imitation learning to enable an…

Recently, a multitude of methods for image-to-image translation have demonstrated impressive results on problems such as multi-domain or multi-attribute transfer. The vast majority of such works leverages the strengths of adversarial…

Zero-shot imitation learning algorithms hold the promise of reproducing unseen behavior from as little as a single demonstration at test time. Existing practical approaches view the expert demonstration as a sequence of goals, enabling…

Learning predictive models from interaction with the world allows an agent, such as a robot, to learn about how the world works, and then use this learned model to plan coordinated sequences of actions to bring about desired outcomes.…

Imitation learning has traditionally been applied to learn a single task from demonstrations thereof. The requirement of structured and isolated demonstrations limits the scalability of imitation learning approaches as they are difficult to…

Imitation learning algorithms learn a policy from demonstrations of expert behavior. We show that, for deterministic experts, imitation learning can be done by reduction to reinforcement learning with a stationary reward. Our theoretical…

We tackle the problem of policy learning from expert demonstrations without a reward function. A central challenge in this space is that these policies fail upon deployment due to issues of distributional shift, environment stochasticity,…

We propose a self-supervised approach for learning representations and robotic behaviors entirely from unlabeled videos recorded from multiple viewpoints, and study how this representation can be used in two robotic imitation settings:…

Human demonstration data is often ambiguous and incomplete, motivating imitation learning approaches that also exhibit reliable planning behavior. A common paradigm to perform planning-from-demonstration involves learning a reward function…

Masked Image Modeling (MIM) has emerged as a promising method for deriving visual representations from unlabeled image data by predicting missing pixels from masked portions of images. It excels in region-aware learning and provides strong…

Imitation Learning (IL) enables agents to mimic expert behavior by learning from demonstrations. However, traditional IL methods require large amounts of medium-to-high-quality demonstrations as well as actions of expert demonstrations,…

The current dominant paradigm for imitation learning relies on strong supervision of expert actions to learn both 'what' and 'how' to imitate. We pursue an alternative paradigm wherein an agent first explores the world without any expert…