Related papers: Back to Reality for Imitation Learning

Over the past decade, the field of machine learning has experienced remarkable advancements. While image recognition systems have achieved impressive levels of accuracy, they continue to rely on extensive training datasets. Additionally, a…

State-of-the-art machine learning algorithms demonstrate close to absolute performance in selected challenges. We provide arguments that the reason can be in low variability of the samples and high effectiveness in learning typical…

Imitation learning in robots, also called programing by demonstration, has made important advances in recent years, allowing humans to teach context dependant motor skills/tasks to robots. We propose to extend the usual contexts…

Imitation learning has achieved great success in many sequential decision-making tasks, in which a neural agent is learned by imitating collected human demonstrations. However, existing algorithms typically require a large number of…

Rapidly applying the effects of detector response to physics objects (e.g. electrons, muons, showers of particles) is essential in high energy physics. Currently available tools for the transformation from truth-level physics objects to…

Evaluation metrics in machine learning are often hardly taken as loss functions, as they could be non-differentiable and non-decomposable, e.g., average precision and F1 score. This paper aims to address this problem by revisiting the…

Imitation learning from observation (LfO) is more preferable than imitation learning from demonstration (LfD) due to the nonnecessity of expert actions when reconstructing the expert policy from the expert data. However, previous studies…

Imitation learning practitioners have often noted that conditioning policies on previous actions leads to a dramatic divergence between "held out" error and performance of the learner in situ. Interactive approaches can provably address…

Imitation learning is the process by which one agent tries to learn how to perform a certain task using information generated by another, often more-expert agent performing that same task. Conventionally, the imitator has access to both…

We are interested in solving the problem of imitation learning with a limited amount of real-world expert data. Existing offline imitation methods often struggle with poor data coverage and severe performance degradation. We propose a…

Providing a suitable reward function to reinforcement learning can be difficult in many real world applications. While inverse reinforcement learning (IRL) holds promise for automatically learning reward functions from demonstrations,…

While machine learning is traditionally a resource intensive task, embedded systems, autonomous navigation and the vision of the Internet-of-Things fuel the interest in resource efficient approaches. These approaches require a carefully…

Imitation learning is a powerful machine learning algorithm for a robot to acquire manipulation skills. Nevertheless, many real-world manipulation tasks involve precise and dexterous robot-object interactions, which make it difficult for…

Imitation learning is a widely used policy learning method that enables intelligent agents to acquire complex skills from expert demonstrations. The input to the imitation learning algorithm is usually composed of both the current…

Bridging the gap between motion models and reality is crucial by using limited data to deploy robots in the real world. Deep learning is expected to be generalized to diverse situations while reducing feature design costs through end-to-end…

The framework of Simulation-to-real learning, i.e, learning policies in simulation and transferring those policies to the real world is one of the most promising approaches towards data-efficient learning in robotics. However, due to the…

Intelligent robots need to generate and execute plans. In order to deal with the complexity of real environments, planning makes some assumptions about the world. When executing plans, the assumptions are usually not met. Most works have…

In imitation learning, an agent learns how to behave in an environment with an unknown cost function by mimicking expert demonstrations. Existing imitation learning algorithms typically involve solving a sequence of planning or…

Imitation learning benchmarks often lack sufficient variation between training and evaluation, limiting meaningful generalisation assessment. We introduce Labyrinth, a benchmarking environment designed to test generalisation with precise…

Observational learning requires an agent to learn to perform a task by referencing only observations of the performed task. This work investigates the equivalent setting in real-world robot learning where access to hand-designed rewards and…