While deep reinforcement learning (RL) has fueled multiple high-profile successes in
machine learning, it is held back from more widespread adoption by its often poor data …

We propose a theoretical framework for studying behavior cloning of complex expert
demonstrations using generative modeling. Our framework invokes low-level controllers …

Learning to solve tasks from a sparse reward signal is a major challenge for standard
reinforcement learning (RL) algorithms. However, in the real world, agents rarely need to …

This paper studies the prediction of a target $\mathbf {z} $ from a pair of random variables
$(\mathbf {x},\mathbf {y}) $, where the ground-truth predictor is additive $\mathbb {E}[\mathbf …

Meta-reinforcement learning (meta-RL) techniques have demonstrated remarkable success
in generalizing deep reinforcement learning across a range of tasks. Nevertheless, these …

We propose a theoretical framework for studying the imitation of stochastic, non-Markovian,
potentially multi-modal (ie" complex") expert demonstrations in nonlinear dynamical …

Harmful data shifts occur when the distribution of data used to train a clinical AI system
differs significantly from the distribution of data encountered during deployment, leading to …

A major challenge of reinforcement learning (RL) in real-world applications is the variation
between environments, tasks or clients. Meta-RL (MRL) addresses this issue by learning a …

The reliable deployment of deep reinforcement learning in real-world settings requires the
ability to generalize across a variety of conditions, including both in-distribution scenarios …

针对传统生成对抗逆强化学习存在的专家样本获取困难以及生成样本利用率低的问题,
提出一种基于事后经验回放策略HER 的双鉴别器生成对抗D2GA 逆强化学习算法. 在该算法中 …