Navigating urban environments represents a complex task for automated vehicles. They must reach their goal safely and efficiently while considering a multitude of traffic participants. We propose a modular decision making algorithm to autonomously navigate intersections, addressing challenges of existing rule-based and reinforcement learning (RL) approaches. We first present a safe RL algorithm relying on a model-checker to ensure safety guarantees. To make the decision strategy robust to perception errors and occlusions, we introduce a belief update technique using a learning based approach. Finally, we use a scene decomposition approach to scale our algorithm to environments with multiple traffic participants. We empirically demonstrate that our algorithm outperforms rule-based methods and reinforcement learning techniques on a complex intersection scenario.

Rather than proposing a new method, this paper investigates an issue present in existing learning algorithms. We study the learning dynamics of reinforcement learning (RL), specifically a characteristic coupling between learning and data generation that arises because RL agents control their future data distribution. In the presence of function approximation, this coupling can lead to a problematic type of 'ray interference', characterized by learning dynamics that sequentially traverse a number of performance plateaus, effectively constraining the agent to learn one thing at a time even when learning in parallel is better. We establish the conditions under which ray interference occurs, show its relation to saddle points and obtain the exact learning dynamics in a restricted setting. We characterize a number of its properties and discuss possible remedies.

Deception plays a key role in adversarial or strategic interactions for the purpose of self-defence and survival. This paper introduces a general framework and solution to address deception. Most existing approaches for deception consider obfuscating crucial information to rational adversaries with abundant memory and computation resources. In this paper, we consider deceiving adversaries with bounded rationality and in terms of expected rewards. This problem is commonly encountered in many applications especially involving human adversaries. Leveraging the cognitive bias of humans in reward evaluation under stochastic outcomes, we introduce a framework to optimally assign resources of a limited quantity to optimally defend against human adversaries. Modeling such cognitive biases follows the so-called prospect theory from behavioral psychology literature. Then we formulate the resource allocation problem as a signomial program to minimize the defender's cost in an environment modeled as a Markov decision process. We use police patrol hour assignment as an illustrative example and provide detailed simulation results based on real-world data.

With increasing physicians' workload and patients' needs for care, there is a need for technology that facilitates physicians work and performs continues follow-up with patients. Existing approaches focus merely on improving patient's condition, and none have considered managing physician's workload. This paper presents an initial evaluation of a conversational agent assisted coaching platform intended to manage physicians' fatigue and provide continuous follow-up to patients. We highlight the approach adapted to build the chatbot dialogue and the coaching platform. We will particularly discuss the activity recommender algorithms used to suggest insights about patients' condition and activities based on previously collected data. The paper makes three contributions: (1) present the conversational agent as an assistive virtual coach, (2) decrease physicians workload and continuous follow up with patients, all by handling some repetitive physician tasks and performing initial follow up with the patient, (3) present the activity recommender that tracks previous activities and patient information and provides useful insights about possible activity and patient match to the coach. Future work focuses on integrating the recommender model with the CoachAI platform and test the prototype with patient's in collaboration with an ambulatory clinic.

We propose a local adversarial disentangling network (LADN) for facial makeup and de-makeup. Central to our method are multiple and overlapping local adversarial discriminators in a content-style disentangling network for achieving local detail transfer between facial images, with the use of asymmetric loss functions for dramatic makeup styles with high-frequency details. Existing techniques do not demonstrate or fail to transfer high-frequency details in a global adversarial setting, or train a single local discriminator only to ensure image structure consistency and thus work only for relatively simple styles. Unlike others, our proposed local adversarial discriminators can distinguish whether the generated local image details are consistent with the corresponding regions in the given reference image in cross-image style transfer in an unsupervised setting. Incorporating these technical contributions, we achieve not only state-of-the-art results on conventional styles but also novel results involving complex and dramatic styles with high-frequency details covering large areas across multiple facial features. A carefully designed dataset of unpaired before and after makeup images will be released.

In line with recent advances in neural drug design 1.1 Motivation and sensitivity prediction, we propose a novel Discovery of novel compounds with a desired efficacy and architecture for interpretable prediction of anticancer improving existing therapies are key bottlenecks in the pharmaceutical compound sensitivity using a multimodal industry, which fuel the largest R&D business attention-based convolutional encoder. Our model spending of any industry and account for 19% of the total is based on the three key pillars of drug sensitivity: R&D spending worldwide (Petrova, 2014; Goh et al., compounds' structure in the form of a SMILES 2017). Anticancer compounds, in particular, take the lion's sequence, gene expression profiles of tumors and share of drug discovery R&D efforts, with over 34% of all prior knowledge on intracellular interactions from drugs in the global R&D pipeline in 2018 (5,212 of 15,267 protein-protein interaction networks. We demonstrate drugs) (Lloyd et al., 2017). Despite enormous scientific that our multiscale convolutional attentionbased and technological advances in recent years, serendipity still (MCA) encoder significantly outperforms a plays a major role in anticancer drug discovery (Hargrave-baseline model trained on Morgan fingerprints, a Thomas et al., 2012) without a systematic way to accumulate selection of encoders based on SMILES as well and leverage years of R&D to achieve higher success as previously reported state of the art for multimodal rates in drug discovery. On the other hand, there is strong drug sensitivity prediction (R2 0.86 evidence that the response to anticancer therapy is highly dependent and RMSE 0.89).

Learning to take actions based on observations is a core requirement for artificial agents to be able to be successful and robust at their task. Reinforcement Learning (RL) is a well-known technique for learning such policies. However, current RL algorithms often have to deal with reward shaping, have difficulties generalizing to other environments and are most often sample inefficient. In this paper, we explore active inference and the free energy principle, a normative theory from neuroscience that explains how self-organizing biological systems operate by maintaining a model of the world and casting action selection as an inference problem. We apply this concept to a typical problem known to the RL community, the mountain car problem, and show how active inference encompasses both RL and learning from demonstrations.

A teenager in New York is suing one of the biggest companies in the world for $1 billion. A New York college student filed a lawsuit against Apple for $1 billion, claiming the company's alleged use of facial recognition software in its stores falsely linked him to a series of Apple store thefts. Ousmane Bah, 18, claims that he received a summons from a court in Boston saying that he stole $1,200 worth of Apple products in 2018, according to papers filed on Monday in Manhattan federal court. The products included Apple Pencils, which retail for $99 each. On the day of one of the thefts in Boston, Bah was attending his senior prom in Manhattan, according to the court documents.

Stephen Crouch of Montana-based Blackmore explains how the company's lidar technology would help a robot car see what's ahead. Waymo will build self-driving vehicles in Detroit. The company, once known as Google's self-driving car project and now a leader in the push to develop autonomous vehicles, had previously said it was scouting locations in southeast Michigan but did not name a specific city. CEO John Krafcik revealed Detroit as the company's choice in a blog post Tuesday titled, "Making Waymos in Motor City." It refers to being "up and running" this year.

Three distinct sounds were detected by NASA's Insight Lander while sitting on Mars' surface. The first "Mars quake" has been detected, NASA announced Tuesday. The finding "officially kicks off a new field: Martian seismology!," said Bruce Banerdt of NASA's Jet Propulsion Laboratory. NASA said this is the first trembling that appears to have come from inside the planet, as opposed to being caused by forces above the surface, such as wind. The sound was detected by NASA's Insight Lander, a robot spacecraft that's now sitting on the Martian surface.