Related papers: Provable Hierarchical Imitation Learning via EM
The options framework for hierarchical reinforcement learning has increased its popularity in recent years and has made improvements in tackling the scalability problem in reinforcement learning. Yet, most of these recent successes are…
We consider the problem of imitation learning from a finite set of expert trajectories, without access to reinforcement signals. The classical approach of extracting the expert's reward function via inverse reinforcement learning, followed…
Hierarchical Reinforcement Learning (HRL) approaches have shown successful results in solving a large variety of complex, structured, long-horizon problems. Nevertheless, a full theoretical understanding of this empirical evidence is…
Imitation learning algorithms learn a policy from demonstrations of expert behavior. We show that, for deterministic experts, imitation learning can be done by reduction to reinforcement learning with a stationary reward. Our theoretical…
We study how to effectively leverage expert feedback to learn sequential decision-making policies. We focus on problems with sparse rewards and long time horizons, which typically pose significant challenges in reinforcement learning. We…
It has been a challenge to learning skills for an agent from long-horizon unannotated demonstrations. Existing approaches like Hierarchical Imitation Learning(HIL) are prone to compounding errors or suboptimal solutions. In this paper, we…
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…
The current thesis aims to explore the reinforcement learning field and build on existing methods to produce improved ones to tackle the problem of learning in high-dimensional and complex environments. It addresses such goals by…
Items in modern recommender systems are often organized in hierarchical structures. These hierarchical structures and the data within them provide valuable information for building personalized recommendation systems. In this paper, we…
Learning options that allow agents to exhibit temporally higher order behavior has proven to be useful in increasing exploration, reducing sample complexity and for various transfer scenarios. Deep Discovery of Options (DDO) is a generative…
Autonomous agents can learn by imitating teacher demonstrations of the intended behavior. Hierarchical control policies are ubiquitously useful for such learning, having the potential to break down structured tasks into simpler sub-tasks,…
How to obtain hierarchical representations with an increasing level of abstraction becomes one of the key issues of learning with deep neural networks. A variety of RNN models have recently been proposed to incorporate both explicit and…
One of the key challenges in applying reinforcement learning to real-life problems is that the amount of train-and-error required to learn a good policy increases drastically as the task becomes complex. One potential solution to this…
Quantifying the data uncertainty in learning tasks is often done by learning a prediction interval or prediction set of the label given the input. Two commonly desired properties for learned prediction sets are \emph{valid coverage} and…
Humans can leverage hierarchical structures to split a task into sub-tasks and solve problems efficiently. Both imitation and reinforcement learning or a combination of them with hierarchical structures have been proven to be an efficient…
Reinforcement learning in complex environments is a challenging problem. In particular, the success of reinforcement learning algorithms depends on a well-designed reward function. Inverse reinforcement learning (IRL) solves the problem of…
Hierarchical reinforcement learning (HRL) has seen widespread interest as an approach to tractable learning of complex modular behaviors. However, existing work either assume access to expert-constructed hierarchies, or use…
Learning with hidden variables is a central challenge in probabilistic graphical models that has important implications for many real-life problems. The classical approach is using the Expectation Maximization (EM) algorithm. This…
We propose a new framework for imitation learning -- treating imitation as a two-player ranking-based game between a policy and a reward. In this game, the reward agent learns to satisfy pairwise performance rankings between behaviors,…
Hierarchical Imitation Learning (HIL) has been proposed to recover highly-complex behaviors in long-horizon tasks from expert demonstrations by modeling the task hierarchy with the option framework. Existing methods either overlook the…