Related papers: InfoGAIL: Interpretable Imitation Learning from Vi…
The ability to plan actions on multiple levels of abstraction enables intelligent agents to solve complex tasks effectively. However, learning the models for both low and high-level planning from demonstrations has proven challenging,…
We cast visual imitation as a visual correspondence problem. Our robotic agent is rewarded when its actions result in better matching of relative spatial configurations for corresponding visual entities detected in its workspace and…
Hand-crafting generalised decision-making rules for real-world urban autonomous driving is hard. Alternatively, learning behaviour from easy-to-collect human driving demonstrations is appealing. Prior work has studied imitation learning…
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…
We present the ADaptive Adversarial Imitation Learning (ADAIL) algorithm for learning adaptive policies that can be transferred between environments of varying dynamics, by imitating a small number of demonstrations collected from a single…
We propose a general way to integrate procedural knowledge of a domain into deep learning models. We apply it to the case of video prediction, building on top of object-centric deep models and show that this leads to a better performance…
In-context imitation learning enables robots to adapt to new tasks from a small number of demonstrations without additional training. However, existing approaches typically condition only on state-action trajectories and lack explicit…
Interpretable machine learning tackles the important problem that humans cannot understand the behaviors of complex machine learning models and how these models arrive at a particular decision. Although many approaches have been proposed, a…
Visual imitation learning enables robotic agents to acquire skills by observing expert demonstration videos. In the one-shot setting, the agent generates a policy after observing a single expert demonstration without additional fine-tuning.…
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,…
Interactive imitation learning is an efficient, model-free method through which a robot can learn a task by repetitively iterating an execution of a learning policy and a data collection by querying human demonstrations. However, deploying…
Construction robots are challenging the traditional paradigm of labor intensive and repetitive construction tasks. Present concerns regarding construction robots are focused on their abilities in performing complex tasks consisting of…
In standard passive imitation learning, the goal is to learn a target policy by passively observing full execution trajectories of it. Unfortunately, generating such trajectories can require substantial expert effort and be impractical in…
Imitation learning is an effective tool for robotic learning tasks where specifying a reinforcement learning (RL) reward is not feasible or where the exploration problem is particularly difficult. Imitation, typically behavior cloning or…
Imitation learning for acquiring generalizable policies often requires a large volume of demonstration data, making the process significantly costly. One promising strategy to address this challenge is to leverage the cognitive and…
Learning from Demonstration~(LfD) should capture not only how a task is executed, but also its high-level task structure that explains the demonstrated behavior. As robots become more autonomous, such task representations must be…
In many sequential decision-making problems (e.g., robotics control, game playing, sequential prediction), human or expert data is available containing useful information about the task. However, imitation learning (IL) from a small amount…
Imitation learning (IL) algorithms use expert demonstrations to learn a specific task. Most of the existing approaches assume that all expert demonstrations are reliable and trustworthy, but what if there exist some adversarial…
In this paper, we consider domain-adaptive imitation learning with visual observation, where an agent in a target domain learns to perform a task by observing expert demonstrations in a source domain. Domain adaptive imitation learning…
Passive observational data, such as human videos, is abundant and rich in information, yet remains largely untapped by current RL methods. Perhaps surprisingly, we show that passive data, despite not having reward or action labels, can…