Related papers: Safe Imitation Learning via Fast Bayesian Reward I…

Reinforcement learning offers the promise of automating the acquisition of complex behavioral skills. However, compared to commonly used and well-understood supervised learning methods, reinforcement learning algorithms can be brittle,…

Existing approaches to reward inference from behavior typically assume that humans provide demonstrations according to specific models of behavior. However, humans often indicate their goals through a wide range of behaviors, from actions…

Common approaches to providing feedback in reinforcement learning are the use of hand-crafted rewards or full-trajectory expert demonstrations. Alternatively, one can use examples of completed tasks, but such an approach can be extremely…

In the last decade, deep learning has achieved great success in machine learning tasks where the input data is represented with different levels of abstractions. Driven by the recent research in reinforcement learning using deep neural…

We address the issue of tuning hyperparameters (HPs) for imitation learning algorithms in the context of continuous-control, when the underlying reward function of the demonstrating expert cannot be observed at any time. The vast literature…

Bayesian methods for machine learning have been widely investigated, yielding principled methods for incorporating prior information into inference algorithms. In this survey, we provide an in-depth review of the role of Bayesian methods…

This paper addresses the problem of maintaining safety during training in Reinforcement Learning (RL), such that the safety constraint violations are bounded at any point during learning. In a variety of RL applications the safety of the…

A significant challenge for the practical application of reinforcement learning in the real world is the need to specify an oracle reward function that correctly defines a task. Inverse reinforcement learning (IRL) seeks to avoid this…

Extrapolating beyond-demonstrator (BD) performance through the imitation learning (IL) algorithm aims to learn from and subsequently outperform the demonstrator. To that end, a representative approach is to leverage inverse reinforcement…

We propose a data-efficient Gaussian process-based Bayesian approach to the semi-supervised learning problem on graphs. The proposed model shows extremely competitive performance when compared to the state-of-the-art graph neural networks…

Imitation learning is a class of promising policy learning algorithms that is free from many practical issues with reinforcement learning, such as the reward design issue and the exploration hardness. However, the current imitation…

Designing rewards for Reinforcement Learning (RL) is challenging because it needs to convey the desired task, be efficient to optimize, and be easy to compute. The latter is particularly problematic when applying RL to robotics, where…

High sample complexity has long been a challenge for RL. On the other hand, humans learn to perform tasks not only from interaction or demonstrations, but also by reading unstructured text documents, e.g., instruction manuals. Instruction…

Imitation learning often assumes that demonstrations are close to optimal according to some fixed, but unknown, cost function. However, according to satisficing theory, humans often choose acceptable behavior based on their personal (and…

The goal of reinforcement learning algorithms is to estimate and/or optimise the value function. However, unlike supervised learning, no teacher or oracle is available to provide the true value function. Instead, the majority of…

Imitation learning is an effective alternative approach to learn a policy when the reward function is sparse. In this paper, we consider a challenging setting where an agent and an expert use different actions from each other. We assume…

In imitation learning, it is common to learn a behavior policy to match an unknown target policy via max-likelihood training on a collected set of target demonstrations. In this work, we consider using offline experience datasets -…

Reinforcement Learning algorithms aim to learn optimal control strategies through iterative interactions with an environment. A critical element in this process is the experience replay buffer, which stores past experiences, allowing the…

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,…

We propose WayEx, a new method for learning complex goal-conditioned robotics tasks from a single demonstration. Our approach distinguishes itself from existing imitation learning methods by demanding fewer expert examples and eliminating…