arXiv research

Online Apprenticeship Learning aims to match expert performance without access to cost functions.

We derive and analyze learning algorithms for apprenticeship learning, policy evaluation, and policy gradient for average reward criteria. Existing algorithms explicitly require an upper bound on the mixing time. In contrast, we build on ideas from Markov chain theory and derive sampling algorithms that do not require …

Resource scheduling and coordination is an NP-hard optimization requiring an efficient allocation of agents to a set of tasks with upper- and lower bound temporal and resource constraints. Due to the large-scale and dynamic nature of resource coordination in hospitals and factories, human domain experts manually plan a…

In this paper we present an early Apprenticeship Learning approach to mimic the behaviour of different players in a short adaption of the interactive fiction Anchorhead. Our motivation is the need to understand and simulate player behaviour to create systems to aid the design and personalisation of Interactive Narrativ…

We consider apprenticeship learning, i.e., having an agent learn a task by observing an expert demonstrating the task in a partially observable environment when the model of the environment is uncertain. This setting is useful in applications where the explicit modeling of the environment is difficult, such as a dialog…

We introduce a novel apprenticeship learning algorithm to learn an expert's underlying reward structure in off-policy model-free \emph{batch} settings. Unlike existing methods that require a dynamics model or additional data acquisition for on-policy evaluation, our algorithm requires only the batch data of observed ex…

The paper optimizes UAV path and power for QoS in cellular networks.

This paper reports applications of Difference of Convex functions (DC) programming to Learning from Demonstrations (LfD) and Reinforcement Learning (RL) with expert data. This is made possible because the norm of the Optimal Bellman Residual (OBR), which is at the heart of many RL and LfD algorithms, is DC. Improvement…

We consider the applications of the Frank-Wolfe (FW) algorithm for Apprenticeship Learning (AL). In this setting, we are given a Markov Decision Process (MDP) without an explicit reward function. Instead, we observe an expert that acts according to some policy, and the goal is to find a policy whose feature expectation…

In this paper we propose a novel gradient algorithm to learn a policy from an expert's observed behavior assuming that the expert behaves optimally with respect to some unknown reward function of a Markovian Decision Problem. The algorithm's aim is to find a reward function such that the resulting optimal policy matche…

Imitation learning trains a policy from expert demonstrations. Imitation learning approaches have been designed from various principles, such as behavioral cloning via supervised learning, apprenticeship learning via inverse reinforcement learning, and GAIL via generative adversarial learning. In this paper, we propose…

Reward suffices for convex MDPs, expanding RL to new problems.

A new method for learning policies from demonstrations without reinforcement.

Background: Virtual reality simulators and machine learning have the potential to augment understanding, assessment and training of psychomotor performance in neurosurgery residents. Objective: This study outlines the first application of machine learning to distinguish "skilled" and "novice" psychomotor performance du…

New method learns to answer questions from correct demonstrations without assuming bounded complexity of the demonstrator.

Meta-learning adapts models for unseen tasks across AI, robotics, and NLP.

Meta-learning improves neural networks by adapting learning algorithms.

Survey explores how transfer learning improves deep reinforcement learning.

New method uses bi-level optimization to learn useful representations for imitation learning.

Study Whittle index learning algorithms for restless bandits with constant stepsizes.

AI learns to learn sequentially without forgetting.

Poisson learning doesn't solve graph semi-supervised learning issues.

New unsupervised learning technique learns independent kernels for better machine learning tasks.

Meta-learning helps models learn quickly from few samples.

New self-imitation learning method improves performance in continuous control tasks.

Deep reinforcement learning finds optimal learning policies for adaptive systems.

Unified framework explains all types of learning, including brain.

Cyclical learning rates improve DRL performance without manual tuning.

Study batch reinforcement learning methods for personalized medical treatments.

A new meta-meta classification method tackles few-shot learning tasks.

The paper proposes a learning algorithm that improves adaptability and generalization.

This paper surveys meta-learning, online, and continual learning.

Relational logistic regression (RLR) is a representation of conditional probability in terms of weighted formulae for modelling multi-relational data. In this paper, we develop a learning algorithm for RLR models. Learning an RLR model from data consists of two steps: 1- learning the set of formulae to be used in the m…

Survey on curriculum learning for reinforcement learning.

Contrastive learning works well with redundant data views.

Paper analyzes iterative learning for concept classes and learns half-spaces.

This paper introduces Dex, a reinforcement learning environment toolkit specialized for training and evaluation of continual learning methods as well as general reinforcement learning problems. We also present the novel continual learning method of incremental learning, where a challenging environment is solved using o…

Study shows cliff-learning in transfer learning from foundation models.

Meta-strategy learns tuning parameters for online learning methods.

We discuss a general method to learn data representations from multiple tasks. We provide a justification for this method in both settings of multitask learning and learning-to-learn. The method is illustrated in detail in the special case of linear feature learning. Conditions on the theoretical advantage offered by m…

Compared to reinforcement learning, imitation learning (IL) is a powerful paradigm for training agents to learn control policies efficiently from expert demonstrations. However, in most cases, obtaining demonstration data is costly and laborious, which poses a significant challenge in some scenarios. A promising altern…

Machine can learn its own bias from related tasks.

This paper aims to define out-of-distribution learning.

This paper reviews and proposes a unified framework for contrastive learning.

This survey reviews Heterogeneous Representation Learning (HRL) for diverse data types.

Unified deep metric learning approach using neural networks.

Reinforcement learning mimics expert behavior.

New approach for large-scale distributed learning systems that improve generalization performance.