相关论文: Bayesian Experience Reuse for Learning from Multip…

Residual reinforcement learning (RL) has been proposed as a way to solve challenging robotic tasks by adapting control actions from a conventional feedback controller to maximize a reward signal. We extend the residual formulation to learn…

We introduce a new method for learning Bayesian neural networks, treating them as a stack of multivariate Bayesian linear regression models. The main idea is to infer the layerwise posterior exactly if we know the target outputs of each…

Machine learning strategies like multi-task learning, meta-learning, and transfer learning enable efficient adaptation of machine learning models to specific applications in healthcare, such as prediction of various diseases, by leveraging…

Bayesian inversion is central to the quantification of uncertainty within problems arising from numerous applications in science and engineering. To formulate the approach, four ingredients are required: a forward model mapping the unknown…

Our goal is to deploy a high-accuracy system starting with zero training examples. We consider an "on-the-job" setting, where as inputs arrive, we use real-time crowdsourcing to resolve uncertainty where needed and output our prediction…

Learning from Demonstration (LfD) provides an intuitive and fast approach to program robotic manipulators. Task parameterized representations allow easy adaptation to new scenes and online observations. However, this approach has been…

Inverse Reinforcement Learning addresses the problem of inferring an expert's reward function from demonstrations. However, in many applications, we not only have access to the expert's near-optimal behavior, but we also observe part of her…

Domain experts often possess valuable physical insights that are overlooked in fully automated decision-making processes such as Bayesian optimisation. In this article we apply high-throughput (batch) Bayesian optimisation alongside…

We present an iterative active constraint learning (ACL) algorithm, within the learning from demonstrations (LfD) paradigm, which intelligently solicits informative demonstration trajectories for inferring an unknown constraint in the…

Bayesian experimental design (BED) has been used as a method for conducting efficient experiments based on Bayesian inference. The existing methods, however, mostly focus on maximizing the expected information gain (EIG); the cost of…

Meta-learning methods perform well on new within-distribution tasks but often fail when adapting to out-of-distribution target tasks, where transfer from source tasks can induce negative transfer. We propose a causally-aware Bayesian…

Practical Imitation Learning (IL) systems rely on large human demonstration datasets for successful policy learning. However, challenges lie in maintaining the quality of collected data and addressing the suboptimal nature of some…

Automating robotic surgery via learning from demonstration (LfD) techniques is extremely challenging. This is because surgical tasks often involve sequential decision-making processes with complex interactions of physical objects and have…

Data-efficient learning algorithms are essential in many practical applications where data collection is expensive, e.g., in robotics due to the wear and tear. To address this problem, meta-learning algorithms use prior experience about…

Federated learning (FL) enables collaborative model training across distributed clients while preserving data privacy. However, data and system heterogeneity often cause catastrophic forgetting and unbounded drift in model updates, leading…

Reinforcement learning can learn amortised design policies for designing sequences of experiments. However, current amortised methods rely on estimators of expected information gain (EIG) that require an exponential number of samples on the…

We address the problem of Bayesian reinforcement learning using efficient model-based online planning. We propose an optimism-free Bayes-adaptive algorithm to induce deeper and sparser exploration with a theoretical bound on its performance…

Learn-to-Defer is a paradigm that enables learning algorithms to work not in isolation but as a team with human experts. In this paradigm, we permit the system to defer a subset of its tasks to the expert. Although there are currently…

Meta-learning aims to extract useful inductive biases from a set of related datasets. In Bayesian meta-learning, this is typically achieved by constructing a prior distribution over neural network parameters. However, specifying families of…

This paper studies multiparty learning, aiming to learn a model using the private data of different participants. Model reuse is a promising solution for multiparty learning, assuming that a local model has been trained for each party.…