The NetHack Learning Environment (NLE) is a Reinforcement Learning environment presented at NeurIPS 2020. NLE is based on NetHack 3.6.6 and designed to provide a standard RL interface to the game, and comes with tasks that function as a first step to evaluate agents on this new environment. NetHack is one of the oldest and arguably most impactful videogames in history, as well as being one of the hardest roguelikes currently being played by humans. It is procedurally generated, rich in entities and dynamics, and overall an extremely challenging environment for current state-of-the-art RL agents, while being much cheaper to run compared to other challenging testbeds. Through NLE, we wish to establish NetHack as one of the next challenges for research in decision making and machine learning.

Detecting anomalous trajectories has become an important task in many location-based applications. While many approaches have been proposed for this task, they suffer from various issues including (1) incapability of detecting anomalous subtrajectories, which are finer-grained anomalies in trajectory data, and/or (2) non-data driven, and/or (3) requirement of sufficient supervision labels which are costly to collect. In this paper, we propose a novel reinforcement learning based solution called RL4OASD, which avoids all aforementioned issues of existing approaches. RL4OASD involves two networks, one responsible for learning features of road networks and trajectories and the other responsible for detecting anomalous subtrajectories based on the learned features, and the two networks can be trained iteratively without labeled data. Extensive experiments are conducted on two real datasets, and the results show that our solution can significantly outperform the state-of-the-art methods (with 20-30% improvement) and is efficient for online detection (it takes less than 0.1ms to process each newly generated data point).

As the popularity of graph data increases, there is a growing need to count the occurrences of subgraph patterns of interest, for a variety of applications. Many graphs are massive in scale and also fully dynamic (with insertions and deletions of edges), rendering exact computation of these counts to be infeasible. Common practice is, instead, to use a small set of edges as a sample to estimate the counts. Existing sampling algorithms for fully dynamic graphs sample the edges with uniform probability. In this paper, we show that we can do much better if we sample edges based on their individual properties. Specifically, we propose a weighted sampling algorithm called WSD for estimating the subgraph count in a fully dynamic graph stream, which samples the edges based on their weights that indicate their importance and reflect their properties. We determine the weights of edges in a data-driven fashion, using a novel method based on reinforcement learning. We conduct extensive experiments to verify that our technique can produce estimates with smaller errors while often running faster compared with existing algorithms.

Human decision-making often involves combining similar states into categories and reasoning at the level of the categories rather than the actual states. Guided by this intuition, we propose a novel method for clustering state features in deep reinforcement learning (RL) methods to improve their interpretability. Specifically, we propose a plug-and-play framework termed \emph{vector quantized reinforcement learning} (VQ-RL) that extends classic RL pipelines with an auxiliary classification task based on vector quantized (VQ) encoding and aligns with policy training. The VQ encoding method categorizes features with similar semantics into clusters and results in tighter clusters with better separation compared to classic deep RL methods, thus enabling neural models to learn similarities and differences between states better. Furthermore, we introduce two regularization methods to help increase the separation between clusters and avoid the risks associated with VQ training. In simulations, we demonstrate that VQ-RL improves interpretability and investigate its impact on robustness and generalization of deep RL.

This paper studies reinforcement learning (RL) in doubly inhomogeneous environments under temporal non-stationarity and subject heterogeneity. In a number of applications, it is commonplace to encounter datasets generated by system dynamics that may change over time and population, challenging high-quality sequential decision making. Nonetheless, most existing RL solutions require either temporal stationarity or subject homogeneity, which would result in sub-optimal policies if both assumptions were violated. To address both challenges simultaneously, we propose an original algorithm to determine the ``best data chunks" that display similar dynamics over time and across individuals for policy learning, which alternates between most recent change point detection and cluster identification. Our method is general, and works with a wide range of clustering and change point detection algorithms. It is multiply robust in the sense that it takes multiple initial estimators as input and only requires one of them to be consistent. Moreover, by borrowing information over time and population, it allows us to detect weaker signals and has better convergence properties when compared to applying the clustering algorithm per time or the change point detection algorithm per subject. Empirically, we demonstrate the usefulness of our method through extensive simulations and a real data application.

Abstract: Unsupervised image translation using adversarial learning has been attracting attention to improve the image quality of medical images. However, adversarial training based on the global evaluation values of discriminators does not provide sufficient translation performance for locally different image features. We propose adversarial learning with a feedback mechanism from a discriminator to improve the quality of CBCT images. This framework employs U-net as the discriminator and outputs a probability map representing the local discrimination results. The probability map is fed back to the generator and used for training to improve the image translation. Our experiments using 76 corresponding CT-CBCT images confirmed that the proposed framework could capture more diverse image features than conventional adversarial learning frameworks and produced synthetic images with pixel values close to the reference image and a correlation coefficient of 0.93.

Abstract: Unsupervised domain adaptation(UDA) has been applied to image semantic segmentation to solve the problem of domain offset. However, in some difficult categories with poor recognition accuracy, the segmentation effects are still not ideal. To this end, in this paper, Intra-subdomain adaptation adversarial learning segmentation method based on Dynamic Pseudo Labels(IDPL) is proposed. The whole process consists of 3 steps: Firstly, the instance-level pseudo label dynamic generation module is proposed, which fuses the class matching information in global classes and local instances, thus adaptively generating the optimal threshold for each class, obtaining high-quality pseudo labels. Secondly, the subdomain classifier module based on instance confidence is constructed, which can dynamically divide the target domain into easy and difficult subdomains according to the relative proportion of easy and difficult instances. Finally, the subdomain adversarial learning module based on self-attention is proposed.

You will learn four important things. The first one is how to implement games using gym and how to play games for relaxation and having fun. The second one is that you will learn how to preprocess data in reinforcement learning tasks such as in computer games. For practical machine learning applications, you will spend a great deal of time understanding and refining data, which affects the performance of an AI system a lot. The third one is the deep Q-learning algorithm.

It would be useful for machines to use computers as humans do so that they can aid us in everyday tasks. This is a setting in which there is also the potential to leverage large-scale expert demonstrations and human judgements of interactive behaviour, which are two ingredients that have driven much recent success in AI. Here we investigate the setting of computer control using keyboard and mouse, with goals specified via natural language. Instead of focusing on hand-designed curricula and specialized action spaces, we focus on developing a scalable method centered on reinforcement learning combined with behavioural priors informed by actual human-computer interactions. We achieve state-of-the-art and human-level mean performance across all tasks within the MiniWob++ benchmark, a challenging suite of computer control problems, and find strong evidence of cross-task transfer. These results demonstrate the usefulness of a unified human-agent interface when training machines to use computers. Altogether our results suggest a formula for achieving competency beyond MiniWob++ and towards controlling computers, in general, as a human would.

Preference-based reinforcement learning (RL) algorithms help avoid the pitfalls of hand-crafted reward functions by distilling them from human preference feedback, but they remain impractical due to the burdensome number of labels required from the human, even for relatively simple tasks. In this work, we demonstrate that encoding environment dynamics in the reward function (REED) dramatically reduces the number of preference labels required in state-of-the-art preference-based RL frameworks. We hypothesize that REED-based methods better partition the state-action space and facilitate generalization to state-action pairs not included in the preference dataset. REED iterates between encoding environment dynamics in a state-action representation via a self-supervised temporal consistency task, and bootstrapping the preference-based reward function from the state-action representation. Whereas prior approaches train only on the preference-labelled trajectory pairs, REED exposes the state-action representation to all transitions experienced during policy training. We explore the benefits of REED within the PrefPPO [1] and PEBBLE [2] preference learning frameworks and demonstrate improvements across experimental conditions to both the speed of policy learning and the final policy performance. For example, on quadruped-walk and walker-walk with 50 preference labels, REED-based reward functions recover 83% and 66% of ground truth reward policy performance and without REED only 38\% and 21\% are recovered. For some domains, REED-based reward functions result in policies that outperform policies trained on the ground truth reward.