As humans, our goals and our environment are persistently changing throughout our lifetime based on our experiences, actions, and internal and external drives. In contrast, typical reinforcement learning problem set-ups consider decision processes that are stationary across episodes. Can we develop reinforcement learning algorithms that can cope with the persistent change in the former, more realistic problem settings? While on-policy algorithms such as policy gradients in principle can be extended to non-stationary settings, the same cannot be said for more efficient off-policy algorithms that replay past experiences when learning. In this work, we formalize this problem setting, and draw upon ideas from the online learning and probabilistic inference literature to derive an off-policy RL algorithm that can reason about and tackle such lifelong non-stationarity. Our method leverages latent variable models to learn a representation of the environment from current and past experiences, and performs off-policy RL with this representation. We further introduce several simulation environments that exhibit lifelong non-stationarity, and empirically find that our approach substantially outperforms approaches that do not reason about environment shift.

We study how representation learning can accelerate reinforcement learning from rich observations, such as images, without relying either on domain knowledge or pixel-reconstruction. Our goal is to learn representations that both provide for effective downstream control and invariance to task-irrelevant details. Bisimulation metrics quantify behavioral similarity between states in continuous MDPs, which we propose using to learn robust latent representations which encode only the task-relevant information from observations. Our method trains encoders such that distances in latent space equal bisimulation distances in state space. We demonstrate the effectiveness of our method at disregarding task-irrelevant information using modified visual MuJoCo tasks, where the background is replaced with moving distractors and natural videos, while achieving SOTA performance. We also test a first-person highway driving task where our method learns invariance to clouds, weather, and time of day. Finally, we provide generalization results drawn from properties of bisimulation metrics, and links to causal inference.

The article presents a study of the Particle Swarm optimization method for scheduling problem. To improve the method's performance a restriction of particles' velocity and an evolutionary meta-optimization were realized. The approach proposed uses the Genetic algorithms for selection of the parameters of Particle Swarm optimization. Experiments were carried out on test tasks of the job-shop scheduling problem. This research proves the applicability of the approach and shows the importance of tuning the behavioral parameters of the swarm intelligence methods to achieve a high performance.

We aim for mobile robots to function in a variety of common human environments. Such robots need to be able to reason about the locations of previously unseen target objects. Landmark objects can help this reasoning by narrowing down the search space significantly. More specifically, we can exploit background knowledge about common spatial relations between landmark and target objects. For example, seeing a table and knowing that cups can often be found on tables aids the discovery of a cup. Such correlations can be expressed as distributions over possible pairing relationships of objects. In this paper, we propose an active visual object search strategy method through our introduction of the Semantic Linking Maps (SLiM) model. SLiM simultaneously maintains the belief over a target object's location as well as landmark objects' locations, while accounting for probabilistic inter-object spatial relations. Based on SLiM, we describe a hybrid search strategy that selects the next best view pose for searching for the target object based on the maintained belief. We demonstrate the efficiency of our SLiM-based search strategy through comparative experiments in simulated environments. We further demonstrate the real-world applicability of SLiM-based search in scenarios with a Fetch mobile manipulation robot.

Physical reasoning requires forward prediction: the ability to forecast what will happen next given some initial world state. We study the performance of state-of-the-art forward-prediction models in complex physical-reasoning tasks. We do so by incorporating models that operate on object or pixel-based representations of the world, into simple physical-reasoning agents. We find that forward-prediction models improve the performance of physical-reasoning agents, particularly on complex tasks that involve many objects. However, we also find that these improvements are contingent on the training tasks being similar to the test tasks, and that generalization to different tasks is more challenging. Surprisingly, we observe that forward predictors with better pixel accuracy do not necessarily lead to better physical-reasoning performance. Nevertheless, our best models set a new state-of-the-art on the PHYRE benchmark for physical reasoning.

Word embeddings learn implicit biases from linguistic regularities captured by word co-occurrence information. As a result, statistical methods can detect and quantify social biases as well as widely shared associations imbibed by the corpus the word embeddings are trained on. By extending methods that quantify human-like biases in word embeddings, we introduce ValNorm, a new word embedding intrinsic evaluation task, and the first unsupervised method that estimates the affective meaning of valence in words with high accuracy. The correlation between human scores of valence for 399 words collected to establish pleasantness norms in English and ValNorm scores is r=0.88. These 399 words, obtained from social psychology literature, are used to measure biases that are non-discriminatory among social groups. We hypothesize that the valence associations for these words are widely shared across languages and consistent over time. We estimate valence associations of these words using word embeddings from six languages representing various language structures and from historical text covering 200 years. Our method achieves consistently high accuracy, suggesting that the valence associations for these words are widely shared. In contrast, we measure gender stereotypes using the same set of word embeddings and find that social biases vary across languages. Our results signal that valence associations of this word set represent widely shared associations and consequently an intrinsic quality of words.

We study the effect of persistence of engagement on learning in a stochastic multi-armed bandit setting. In advertising and recommendation systems, repetition effect includes a wear-in period, where the user's propensity to reward the platform via a click or purchase depends on how frequently they see the recommendation in the recent past. It also includes a counteracting wear-out period, where the user's propensity to respond positively is dampened if the recommendation was shown too many times recently. Priming effect can be naturally modelled as a temporal constraint on the strategy space, since the reward for the current action depends on historical actions taken by the platform. We provide novel algorithms that achieves sublinear regret in time and the relevant wear-in/wear-out parameters. The effect of priming on the regret upper bound is also additive, and we get back a guarantee that matches popular algorithms such as the UCB1 and Thompson sampling when there is no priming effect. Our work complements recent work on modeling time varying rewards, delays and corruptions in bandits, and extends the usage of rich behavior models in sequential decision making settings.

The 'Clever Hans' effect occurs when the learned model produces correct predictions based on the 'wrong' features. This effect which undermines the generalization capability of an ML model and goes undetected by standard validation techniques has been frequently observed for supervised learning where the training algorithm leverages spurious correlations in the data. The question whether Clever Hans also occurs in unsupervised learning, and in which form, has received so far almost no attention. Therefore, this paper will contribute an explainable AI (XAI) procedure that can highlight the relevant features used by popular anomaly detection models of different type. Our analysis reveals that the Clever Hans effect is widespread in anomaly detection and occurs in many (unexpected) forms. Interestingly, the observed Clever Hans effects are in this case not so much due to the data, but due to the anomaly detection models themselves whose structure makes them unable to detect the truly relevant features, even though vast amounts of data points are available. Overall, our work contributes a warning against an unrestrained use of existing anomaly detection models in practical applications, but it also points at a possible way out of the Clever Hans dilemma, specifically, by allowing multiple anomaly models to mutually cancel their individual structural weaknesses to jointly produce a better and more trustworthy anomaly detector.

Various structured output prediction problems (e.g., sequential tagging) involve constraints over the output space. By identifying these constraints, we can filter out infeasible solutions and build an accountable model. To this end, we present a general integer linear programming (ILP) framework for mining constraints from data. We model the inference of structured output prediction as an ILP problem. Then, given the coefficients of the objective function and the corresponding solution, we mine the underlying constraints by estimating the outer and inner polytopes of the feasible set. We verify the proposed constraint mining algorithm in various synthetic and real-world applications and demonstrate that the proposed approach successfully identifies the feasible set at scale. In particular, we show that our approach can learn to solve 9x9 Sudoku puzzles and minimal spanning tree problems from examples without providing the underlying rules. We also demonstrate results on hierarchical multi-label classification and conduct a theoretical analysis on how close the mined constraints are from the ground truth.

The effects of traffic congestion are adverse, primarily including air pollution, commuter stress, and an increase in vehicle operating costs and accidents on the road. In efforts to alleviate these problems in metropolitan cities, logistics companies plan to introduce a new method of everyday commute called air taxis, an Urban Air Mobility (UAM) service. These are electric-powered vehicles that are expected to operate in the forthcoming years by international transportation companies like Airbus, Uber, and Kitty Hawk. Since these flying taxis are emerging mode of transportation, it is necessary to provide recommendations for the initial design, implementation, and operation. This study proposes managerial insights for these upcoming services by analyzing online customer reviews and conducting an internal assessment of helicopter operations. Helicopters are similar to air taxis in regards to their operations, and therefore, customer reviews pertaining to the former can enable us to obtain insights into the strengths and weaknesses of the short-distance aviation service, in general. A four-stage sequential approach is used in this research, wherein the online reviews are mined in Stage 1, analyzed using the bigram and trigram models in Stage 2, 7S internal assessment is conducted for helicopter services in Stage 3, and managerial recommendations for air taxis are proposed in Stage 4. The insights obtained in this paper could assist any air taxi companies in providing better customer service when they venture into the market. Keywords: Air taxi; Emerging technology; Urban Air Mobility (UAM); Helicopter services; Online customer reviews; Text analytics;