相关论文: Data-efficient Domain Randomization with Bayesian …

Autonomous navigation in unstructured environments is essential for field and planetary robotics, where robots must efficiently reach goals while avoiding obstacles under uncertain conditions. Conventional algorithmic approaches often…

Deep reinforcement learning (DRL) is a promising approach to solve complex control tasks by learning policies through interactions with the environment. However, the training of DRL policies requires large amounts of training experiences,…

We propose a method to predict the sim-to-real transfer performance of RL policies. Our transfer metric simplifies the selection of training setups (such as algorithm, hyperparameters, randomizations) and policies in simulation, without the…

Robotic control policies learned from human demonstrations have achieved impressive results in many real-world applications. However, in scenarios where initial performance is not satisfactory, as is often the case in novel open-world…

Objective: When training machine learning models, we often assume that the training data and evaluation data are sampled from the same distribution. However, this assumption is violated when the model is evaluated on another unseen but…

Training deep neural network policies end-to-end for real-world applications so far requires big demonstration datasets in the real world or big sets consisting of a large variety of realistic and closely related 3D CAD models. These real…

Bayesian optimisation is a well-known sample-efficient method for the optimisation of expensive black-box functions. However when dealing with big search spaces the algorithm goes through several low function value regions before reaching…

Most visual recognition methods implicitly assume the data distribution remains unchanged from training to testing. However, in practice domain shift often exists, where real-world factors such as lighting and sensor type change between…

Deep reinforcement learning (DRL) has shown remarkable success in simulation domains, yet its application in designing robot controllers remains limited, due to its single-task orientation and insufficient adaptability to environmental…

The industrial application of Deep Reinforcement Learning (DRL) is frequently slowed down because of the inability to generate the experience required to train the models. Collecting data often involves considerable time and economic effort…

This paper addresses the problem of unsupervised domain adaption from theoretical and algorithmic perspectives. Existing domain adaptation theories naturally imply minimax optimization algorithms, which connect well with the domain…

Sim2real transfer is primarily concerned with transferring policies trained in simulation to potentially noisy real world environments. A common problem associated with sim2real transfer is estimating the real-world environmental parameters…

In robotic vision, a de-facto paradigm is to learn in simulated environments and then transfer to real-world applications, which poses an essential challenge in bridging the sim-to-real domain gap. While mainstream works tackle this problem…

Global optimisation to optimise expensive-to-evaluate black-box functions without gradient information. Bayesian optimisation, one of the most well-known techniques, typically employs Gaussian processes as surrogate models, leveraging their…

In the Bayesian reinforcement learning (RL) setting, a prior distribution over the unknown problem parameters -- the rewards and transitions -- is assumed, and a policy that optimizes the (posterior) expected return is sought. A common…

Parameter-space regularization in neural network optimization is a fundamental tool for improving generalization. However, standard parameter-space regularization methods make it challenging to encode explicit preferences about desired…

While deep reinforcement learning (RL) agents have demonstrated incredible potential in attaining dexterous behaviours for robotics, they tend to make errors when deployed in the real world due to mismatches between the training and…

Reinforcement learning methods are increasingly used to optimise dialogue policies from experience. Most current techniques are model-free: they directly estimate the utility of various actions, without explicit model of the interaction…

Robotic systems driven by artificial muscles present unique challenges due to the nonlinear dynamics of actuators and the complex designs of mechanical structures. Traditional model-based controllers often struggle to achieve desired…

We introduce the domain adaptation and randomization approach for calibrating neural network-based equalizers for real transmissions, using synthetic data. The approach renders up to 99\% training process reduction, which we demonstrate in…