Related papers: Policy Entropy for Out-of-Distribution Classificat…

Effective reinforcement learning requires a proper balance of exploration and exploitation defined by the dispersion of action distribution. However, this balance depends on the task, the current stage of the learning process, and the…

Traditional training of deep classifiers yields overconfident models that are not reliable under dataset shift. We propose a Bayesian framework to obtain reliable uncertainty estimates for deep classifiers. Our approach consists of a…

An issue concerning the use of deep reinforcement learning (RL) agents is whether they can be trusted to perform reliably when deployed, as training environments may not reflect real-life environments. Anticipating instances outside their…

We apply diffusion strategies to develop a fully-distributed cooperative reinforcement learning algorithm in which agents in a network communicate only with their immediate neighbors to improve predictions about their environment. The…

The lack of well-calibrated confidence estimates makes neural networks inadequate in safety-critical domains such as autonomous driving or healthcare. In these settings, having the ability to abstain from making a prediction on…

Deep neural networks have achieved great success in classification tasks during the last years. However, one major problem to the path towards artificial intelligence is the inability of neural networks to accurately detect samples from…

Generalization and adaptation of learned skills to novel situations is a core requirement for intelligent autonomous robots. Although contextual reinforcement learning provides a principled framework for learning and generalization of…

Uncertainty quantification is one of the central challenges for machine learning in real-world applications. In reinforcement learning, an agent confronts two kinds of uncertainty, called epistemic uncertainty and aleatoric uncertainty.…

This paper aims to establish an entropy-regularized value-based reinforcement learning method that can ensure the monotonic improvement of policies at each policy update. Unlike previously proposed lower-bounds on policy improvement in…

Deep neural network, despite its remarkable capability of discriminating targeted in-distribution samples, shows poor performance on detecting anomalous out-of-distribution data. To address this defect, state-of-the-art solutions choose to…

Reinforcement Learning has emerged as a promising framework for developing adaptive and data-driven strategies, enabling market makers to optimize decision-making policies based on interactions with the limit order book environment. This…

We present an analysis of predictive uncertainty based out-of-distribution detection for different approaches to estimate various models' epistemic uncertainty and contrast it with extreme value theory based open set recognition. While the…

Deep neural networks have attained remarkable performance when applied to data that comes from the same distribution as that of the training set, but can significantly degrade otherwise. Therefore, detecting whether an example is…

Machine learning algorithms often encounter different or "out-of-distribution" (OOD) data at deployment time, and OOD detection is frequently employed to detect these examples. While it works reasonably well in practice, existing…

Composing previously mastered skills to solve novel tasks promises dramatic improvements in the data efficiency of reinforcement learning. Here, we analyze two recent works composing behaviors represented in the form of action-value…

Out-of-distribution recognition forms an important and well-studied problem in deep learning, with the goal to filter out samples that do not belong to the distribution on which a network has been trained. The conclusion of this paper is…

In this paper, we propose the first fully push-forward-based distributional reinforcement learning algorithm, named PACER, which consists of a distributional critic, a stochastic actor and a sample-based encourager. Specifically, the…

In an out-of-distribution (OOD) detection problem, samples of known classes(also called in-distribution classes) are used to train a special classifier. In testing, the classifier can (1) classify the test samples of known classes to their…

Exploration is essential in reinforcement learning as an agent relies on trial and error to learn an optimal policy. However, when rewards are sparse, naive exploration strategies, like noise injection, are often insufficient. Intrinsic…

Off-policy learning, referring to the procedure of policy optimization with access only to logged feedback data, has shown importance in various real-world applications, such as search engines, recommender systems, and etc. While the…