Related papers: Learning from Demonstrations via Capability-Aware …

Cognitive diagnosis is a crucial task in computational education, aimed at evaluating students' proficiency levels across various knowledge concepts through exercises. Current models, however, primarily rely on students' answered exercises,…

Encouraged by the remarkable achievements of language and vision foundation models, developing generalist robotic agents through imitation learning, using large demonstration datasets, has become a prominent area of interest in robot…

The rapid progress of large foundation models has accelerated the development of task-specialized agents across diverse domains. However, the effectiveness of agents remains tightly coupled with the quality of training data, while curating…

Imitation learning has emerged as a promising approach for addressing sequential decision-making problems, with the assumption that expert demonstrations are optimal. However, in real-world scenarios, most demonstrations are often…

Decision-making in complex, continuous multi-task environments is often hindered by the difficulty of obtaining accurate models for planning and the inefficiency of learning purely from trial and error. While precise environment dynamics…

Learning goal conditioned control in the real world is a challenging open problem in robotics. Reinforcement learning systems have the potential to learn autonomously via trial-and-error, but in practice the costs of manual reward design,…

Behavioral cloning is an imitation learning technique that teaches an agent how to behave through expert demonstrations. Recent approaches use self-supervision of fully-observable unlabeled snapshots of the states to decode state-pairs into…

This article proposes a method for learning and robotic replication of dynamic collaborative tasks from offline videos. The objective is to extend the concept of learning from demonstration (LfD) to dynamic scenarios, benefiting from widely…

Developing agents that can perform challenging complex tasks is the goal of reinforcement learning. The model-free reinforcement learning has been considered as a feasible solution. However, the state of the art research has been to develop…

We propose to learn tasks directly from visual demonstrations by learning to predict the outcome of human and robot actions on an environment. We enable a robot to physically perform a human demonstrated task without knowledge of the…

Recent progress in state-only imitation learning extends the scope of applicability of imitation learning to real-world settings by relieving the need for observing expert actions. However, existing solutions only learn to extract a…

Reinforcement Learning (RL) in partially observable environments poses significant challenges due to the complexity of learning under uncertainty. While additional information, such as that available in simulations, can enhance training,…

Lifelong learning is a long-standing aim for artificial agents that act in dynamic environments, in which an agent needs to accumulate knowledge incrementally without forgetting previously learned representations. We investigate methods for…

Although reinforcement learning has seen tremendous success recently, this kind of trial-and-error learning can be impractical or inefficient in complex environments. The use of demonstrations, on the other hand, enables agents to benefit…

This paper studies Learning from Observations (LfO) for imitation learning with access to state-only demonstrations. In contrast to Learning from Demonstration (LfD) that involves both action and state supervision, LfO is more practical in…

We examine the problem of transferring a policy learned in a source environment to a target environment with different dynamics, particularly in the case where it is critical to reduce the amount of interaction with the target environment…

We study generalizable policy learning from demonstrations for complex low-level control (e.g., contact-rich object manipulations). We propose a novel hierarchical imitation learning method that utilizes sub-optimal demos. Firstly, we…

We focus on the problem of imitation learning from visual observations, where the learning agent has access to videos of experts as its sole learning source. The challenges of this framework include the absence of expert actions and the…

Imitation learning is a popular approach for training visual navigation policies. However, collecting expert demonstrations for legged robots is challenging as these robots can be hard to control, move slowly, and cannot operate…

World models learn the consequences of actions in vision-based interactive systems. However, in practical scenarios like autonomous driving, noncontrollable dynamics that are independent or sparsely dependent on action signals often exist,…