Related papers: How to Utilize Failure Demo Data?: Effective Data …
Imitation learning is a promising paradigm for training robot control policies, but these policies can suffer from distribution shift, where the conditions at evaluation time differ from those in the training data. A popular approach for…
Learning-based methods for dexterous manipulation have made notable progress in recent years. However, learned policies often still lack reliability and exhibit limited robustness to important factors of variation. One failure pattern that…
We study Imitation Learning (IL) from Observations alone (ILFO) in large-scale MDPs. While most IL algorithms rely on an expert to directly provide actions to the learner, in this setting the expert only supplies sequences of observations.…
Data augmentation has been actively studied for robust neural networks. Most of the recent data augmentation methods focus on augmenting datasets during the training phase. At the testing phase, simple transformations are still widely used…
Pretrained models of code, such as CodeBERT and CodeT5, have become popular choices for code understanding and generation tasks. Such models tend to be large and require commensurate volumes of training data, which are rarely available for…
Within the imitation learning paradigm, training generalist robots requires large-scale datasets obtainable only through diverse curation. Due to the relative ease to collect, human demonstrations constitute a valuable addition when…
When cast into the Deep Reinforcement Learning framework, many robotics tasks require solving a long horizon and sparse reward problem, where learning algorithms struggle. In such context, Imitation Learning (IL) can be a powerful approach…
Despite its promise, imitation learning often fails in long-horizon environments where perfect replication of demonstrations is unrealistic and small errors can accumulate catastrophically. We introduce Cago (Capability-Aware Goal…
Learning from Demonstration depends on a robot learner generalising its learned model to unseen conditions, as it is not feasible for a person to provide a demonstration set that accounts for all possible variations in non-trivial tasks.…
Prediction is an appealing objective for self-supervised learning of behavioral skills, particularly for autonomous robots. However, effectively utilizing predictive models for control, especially with raw image inputs, poses a number of…
A core problem in machine learning is to learn expressive latent variables for model prediction on complex data that involves multiple sub-components in a flexible and interpretable fashion. Here, we develop an approach that improves…
Currently, many machine learning algorithms contain lots of iterations. When it comes to existing large-scale distributed systems, some slave nodes may break down or have lower efficiency. Therefore traditional machine learning algorithm…
In recent years, imitation learning has made progress in the field of robotic manipulation. However, it still faces challenges when addressing complex long-horizon tasks with deformable objects, such as high-dimensional state spaces,…
Limited data has become a major bottleneck in scaling up offline imitation learning (IL). In this paper, we propose enhancing IL performance under limited expert data by introducing a pre-training stage that learns dynamics representations,…
Learning from Demonstration (LfD) is a framework that allows lay users to easily program robots. However, the efficiency of robot learning and the robot's ability to generalize to task variations hinges upon the quality and quantity of the…
Adapting language models (LMs) to new tasks via post-training carries the risk of degrading existing capabilities -- a phenomenon classically known as catastrophic forgetting. In this paper, toward identifying guidelines for mitigating this…
Catastrophic forgetting is a significant challenge in the field of machine learning, particularly in neural networks. When a neural network learns to perform well on a new task, it often forgets its previously acquired knowledge or…
Imitation learning has demonstrated strong performance in robotic manipulation by learning from large-scale human demonstrations. While existing models excel at single-task learning, it is observed in practical applications that their…
Learning from Observations (LfO) is a practical reinforcement learning scenario from which many applications can benefit through the reuse of incomplete resources. Compared to conventional imitation learning (IL), LfO is more challenging…
Presence of bias (in datasets or tasks) is inarguably one of the most critical challenges in machine learning applications that has alluded to pivotal debates in recent years. Such challenges range from spurious associations between…