Related papers: Zero-Shot Transfer in Imitation Learning

Open-ended worlds are those in which there are no pre-specified goals or environmental reward signal. As a consequence, an agent must know how to perform a multitude of tasks. However, when a new task is presented to an agent, we expect it…

Although reinforcement learning (RL) can solve many challenging sequential decision making problems, achieving zero-shot transfer across related tasks remains a challenge. The difficulty lies in finding a good representation for the current…

Deep networks devour millions of precisely annotated images to build their complex and powerful representations. Unfortunately, tasks like autonomous driving have virtually no real-world training data. Repeatedly crashing a car into a tree…

Intelligent agents rely heavily on prior experience when learning a new task, yet most modern reinforcement learning (RL) approaches learn every task from scratch. One approach for leveraging prior knowledge is to transfer skills learned on…

We consider a problem of learning the reward and policy from expert examples under unknown dynamics. Our proposed method builds on the framework of generative adversarial networks and introduces the empowerment-regularized maximum-entropy…

Training a robotic policy from scratch using deep reinforcement learning methods can be prohibitively expensive due to sample inefficiency. To address this challenge, transferring policies trained in the source domain to the target domain…

Recent work has described neural-network-based agents that are trained with reinforcement learning (RL) to execute language-like commands in simulated worlds, as a step towards an intelligent agent or robot that can be instructed by human…

Imitation learning is effective for training agents when expert demonstrations are available, but collecting demonstrations for every complex task in an environment is costly. We study the long-horizon, goal-conditioned setting where a…

Current imitation learning techniques are too restrictive because they require the agent and expert to share the same action space. However, oftentimes agents that act differently from the expert can solve the task just as good. For…

Can we teach a robot to recognize and make predictions for activities that it has never seen before? We tackle this problem by learning models for video from text. This paper presents a hierarchical model that generalizes instructional…

Zero-shot learning (ZSL) aims to recognize unseen classes by exploiting semantic descriptions shared between seen classes and unseen classes. Current methods show that it is effective to learn visual-semantic alignment by projecting…

Imitation learning is often used in addition to reinforcement learning in environments where reward design is difficult or where the reward is sparse, but it is difficult to be able to imitate well in unknown states from a small amount of…

Reinforcement Learning (RL) algorithms can learn robotic control tasks from visual observations, but they often require a large amount of data, especially when the visual scene is complex and unstructured. In this paper, we explore how the…

Imitation based robot learning has recently gained significant attention in the robotics field due to its theoretical potential for transferability and generalizability. However, it remains notoriously costly, both in terms of hardware and…

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…

Practitioners often rely on compute-intensive domain randomization to ensure reinforcement learning policies trained in simulation can robustly transfer to the real world. Due to unmodeled nonlinearities in the real system, however, even…

Biological intelligence can learn to solve many diverse tasks in a data efficient manner by re-using basic knowledge and skills from one task to another. Furthermore, many of such skills are acquired without explicit supervision in an…

Imitation from observation is a computational technique that teaches an agent on how to mimic the behavior of an expert by observing only the sequence of states from the expert demonstrations. Recent approaches learn the inverse dynamics of…

In reinforcement learning applications like robotics, agents usually need to deal with various input/output features when specified with different state/action spaces by their developers or physical restrictions. This indicates unnecessary…

How can we reuse existing knowledge, in the form of available datasets, when solving a new and apparently unrelated target task from a set of unlabeled data? In this work we make a first contribution to answer this question in the context…