Physical construction -- the ability to compose objects, subject to physical dynamics, in order to serve some function -- is fundamental to human intelligence. Here we introduce a suite of challenging physical construction tasks inspired by how children play with blocks, such as matching a target configuration, stacking and attaching blocks to connect objects together, and creating shelter-like structures over target objects. We then examine how a range of modern deep reinforcement learning agents fare on these challenges, and introduce several new approaches which provide superior performance. Our results show that agents which use structured representations (e.g., objects and scene graphs) and structured policies (e.g., object-centric actions) outperform those which use less structured representations, and generalize better beyond their training when asked to reason about larger scenes. Agents which use model-based planning via Monte-Carlo Tree Search also outperform strictly model-free agents in our most challenging construction problems. We conclude that approaches which combine structured representations and reasoning with powerful learning are a key path toward agents that possess rich intuitive physics, scene understanding, and planning.

A long-standing challenge in Reinforcement Learning is enabling agents to learn a model of their environment which can be transferred to solve other problems in a world with the same underlying rules. One reason this is difficult is the challenge of learning accurate models of an environment. If such a model is inaccurate, the agent's plans and actions will likely be sub-optimal, and likely lead to the wrong outcomes. Recent progress in model-based reinforcement learning has improved the ability for agents to learn and use predictive models. In this paper, we extend a recent deep learning architecture which learns a predictive model of the environment that aims to predict only the value of a few key measurements, which are be indicative of an agent's performance. Predicting only a few measurements rather than the entire future state of an environment makes it more feasible to learn a valuable predictive model. We extend this predictive model with a small, evolving neural network that suggests the best goals to pursue in the current state. We demonstrate that this allows the predictive model to transfer to new scenarios where goals are different, and that the adaptive goals can even adjust agent behavior on-line, changing its strategy to fit the current context.

Traditional cyber security techniques have led to an asymmetric disadvantage for defenders. The defender must detect all possible threats at all times from all attackers and defend all systems against all possible exploitation. In contrast, an attacker needs only to find a single path to the defender’s critical information. In this article, we discuss how this asymmetry can be rebalanced using cyber deception to change the attacker’s perception of the network environment, and lead attackers to false beliefs about which systems contain critical information or are critical to a defender’s computing infrastructure. We introduce game theory concepts and models to represent and reason over the use of cyber deception by the defender and the effect it has on attacker perception. Finally, we discuss techniques for combining artificial intelligence algorithms with game theory models to estimate hidden states of the attacker using feedback through payoffs to learn how best to defend the system using cyber deception. It is our opinion that adaptive cyber deception is a necessary component of future information systems and networks. The techniques we present can simultaneously decrease the risks and impacts suffered by defenders and dramatically increase the costs and risks of detection for attackers. Such techniques are likely to play a pivotal role in defending national and international security concerns.

The idea of implementing reinforcement learning in a computer was one of the earliest ideas about the possibility of AI, but reinforcement learning remained on the margin of AI until relatively recently. Today we see reinforcement learning playing essential roles in some of the most impressive AI applications. This article presents observations from the author’s personal experience with reinforcement learning over the most recent 40 years of its history in AI, focusing on striking connections that emerged between largely separate disciplines and on some of the findings that surprised him along the way. These connections and surprises place reinforcement learning in a historical context, and they help explain the success it is finding in modern AI. The article concludes by discussing some of the challenges that need to be faced as reinforcement learning moves out into real world.

Aerial filming is becoming more and more popular thanks to the recent advances in drone technology. It invites many intriguing, unsolved problems at the intersection of aesthetical and scientific challenges. In this work, we propose an intelligent agent which supervises motion planning of a filming drone based on aesthetical values of video shots using deep reinforcement learning. Unlike the current state-of-the-art approaches which mostly require explicit guidance by a human expert, our drone learns how to make favorable shot type selections by experience. We propose a learning scheme which exploits aesthetical features of retrospective shots in order to extract a desirable policy for better prospective shots. We train our agent in realistic AirSim simulations using both hand-crafted and human reward functions. We deploy the same agent on a real DJI M210 drone in order to test generalization capability of our approach to real world conditions. To evaluate the success of our approach in the end, we conduct a comprehensive user study in which participants rate the shots taken using our method and write comments about them.

In the previous blog post we talked about reinforcement learning and its characteristics. We mentioned the process of the agent observing the environment output consisting of a reward and the next state, and then acting upon that. This whole process is a Markov Decision Process or an MDP for short. This blog post is a bit mathy. Grab your coffee and a comfortable chair, and just dive in.

Deep Reinforcement Learning (DRL) algorithms are known to be data inefficient. One reason is that a DRL agent learns both the feature and the policy tabula rasa. Integrating prior knowledge into DRL algorithms is one way to improve learning efficiency since it helps to build helpful representations. In this work, we consider incorporating human knowledge to accelerate the asynchronous advantage actor-critic (A3C) algorithm by pre-training a small amount of non-expert human demonstrations. We leverage the supervised autoencoder framework and propose a novel pre-training strategy that jointly trains a weighted supervised classification loss, an unsupervised reconstruction loss, and an expected return loss. The resulting pre-trained model learns more useful features compared to independently training in supervised or unsupervised fashion. Our pre-training method drastically improved the learning performance of the A3C agent in Atari games of Pong and MsPacman, exceeding the performance of the state-of-the-art algorithms at a much smaller number of game interactions. Our method is light-weight and easy to implement in a single machine. For reproducibility, our code is available at github.com/gabrieledcjr/DeepRL/tree/A3C-ALA2019

An important goal of research in Deep Reinforcement Learning in mobile robotics is to train agents capable of solving complex tasks, which require a high level of scene understanding and reasoning from an egocentric perspective. When trained from simulations, optimal environments should satisfy a currently unobtainable combination of high-fidelity photographic observations, massive amounts of different environment configurations and fast simulation speeds. In this paper we argue that research on training agents capable of complex reasoning can be simplified by decoupling from the requirement of high fidelity photographic observations. We present a suite of tasks requiring complex reasoning and exploration in continuous, partially observable 3D environments. The objective is to provide challenging scenarios and a robust baseline agent architecture that can be trained on mid-range consumer hardware in under 24h. Our scenarios combine two key advantages: (i) they are based on a simple but highly efficient 3D environment (ViZ-Doom) which allows high speed simulation (12000fps); (ii) the scenarios provide the user with a range of difficulty settings, in order to identify the limitations of current state of the art algorithms and network architectures. We aim to increase accessibility to the field of Deep-RL by providing baselines for challenging scenarios where new ideas can be iterated on quickly. We argue that the community should be able to address challenging problems in reasoning of mobile agents without the need for a large compute infrastructure.

Distribution and sample models are two popular model choices in model-based reinforcement learning (MBRL). However, learning these models can be intractable, particularly when the state and action spaces are large. Expectation models, on the other hand, are relatively easier to learn due to their compactness and have also been widely used for deterministic environments. For stochastic environments, it is not obvious how expectation models can be used for planning as they only partially characterize a distribution. In this paper, we propose a sound way of using approximate expectation models for MBRL. In particular, we 1) show that planning with an expectation model is equivalent to planning with a distribution model if the state value function is linear in state features, 2) analyze two common parametrization choices for approximating the expectation: linear and non-linear expectation models, 3) propose a sound model-based policy evaluation algorithm and present its convergence results, and 4) empirically demonstrate the effectiveness of the proposed planning algorithm.

In preoperative planning of left atrial appendage closure (LAAC) with CT angiography, the assessment of the appendage orifice plays a crucial role in choosing an appropriate LAAC device size and a proper C-arm angulation. However, accurate orifice detection is laborious because of the high anatomic variation of the appendage, as well as the unclear orifice position and orientation in the available views. We propose an automatic orifice detection approach performing a search on the principal medial axis of the appendage, where we present an efficient iterative algorithm to grow the axis from the appendage to the left atrium. We propose to use the axis-to-surface distance of the appendage for efficient and effective detection. To localize the necessary initial seed for growing the medial axis, we train an artificial localization agent using an actor-critic reinforcement learning approach, defining the localization as a sequential decision process. The entire detection process takes only about 8 seconds, and the variance of the detected orifice with respect to annotations from two experts is calculated to be significantly small and less than the inter-observer variance. The proposed orifice search on the medial axis of the appendage comparing only its distance from the surface provides a simple, yet robust solution for orifice detection. While being the first fully automatic approach and providing a detection error below the inter-observer difference, our method improved the detection efficiency by eighteen times compared to the existing solution, therefore, can be potentially useful for physicians.