Decision-makers are faced with the challenge of estimating what is likely to happen when they take an action. For instance, if I choose not to treat this patient, are they likely to die? Practitioners commonly use supervised learning algorithms to fit predictive models that help decision-makers reason about likely future outcomes, but we show that this approach is unreliable, and sometimes even dangerous. The key issue is that supervised learning algorithms are highly sensitive to the policy used to choose actions in the training data, which causes the model to capture relationships that do not generalize. We propose using a different learning objective that predicts counterfactuals instead of predicting outcomes under an existing action policy as in supervised learning. To support decision-making in temporal settings, we introduce the Counterfactual Gaussian Process (CGP) to predict the counterfactual future progression of continuous-time trajectories under sequences of future actions. We demonstrate the benefits of the CGP on two important decision-support tasks: risk prediction and "what if?" reasoning for individualized treatment planning.

Each Summit offers a comprehensive overview of a specific game industry discipline, and the AI Summit is no exception. This year, for example, Guerrilla Games' Julian Berteling will be delivering a very cool talk on "Beyond'Killzone': Creating New AI Systems for'Horizon Zero Dawn'" to explain the changes that Guerilla made to switch from having to support a single human enemy in closed corridor spaces to a game with more than 25 wildly different characters in a large open world. You'll want to see this, because attendees will learn ways of dealing with an expanding scope of AI, either throughout a single title's production or when moving to a new title. Additionally, attendees will understand concrete methods for dealing with navigation, movement, and animation for open world titles with many, widely varied agents. And in her Summit session on "'Race for the Galaxy': A Neural Network in Production" Temple Gate chief Theresa Duringer will explain how the studio's game Race for the Galaxy (a digital adaptation of the board game) uses temporal difference learning to power its AI.

Deep reinforcement learning (RL) methods generally engage in exploratory behavior through noise injection in the action space. An alternative is to add noise directly to the agent's parameters, which can lead to more consistent exploration and a richer set of behaviors. Methods such as evolutionary strategies use parameter perturbations, but discard all temporal structure in the process and require significantly more samples. Combining parameter noise with traditional RL methods allows to combine the best of both worlds. We demonstrate that both off- and on-policy methods benefit from this approach through experimental comparison of DQN, DDPG, and TRPO on high-dimensional discrete action environments as well as continuous control tasks. Our results show that RL with parameter noise learns more efficiently than traditional RL with action space noise and evolutionary strategies individually.

Reinforcement Learning (RL) is a research area that has blossomed tremendously in recent years and has shown remarkable potential for artificial intelligence based opponents in computer games. This success is primarily due to vast capabilities of Convolutional Neural Networks (ConvNet), enabling algorithms to extract useful information from noisy environments. Capsule Network (CapsNet) is a recent introduction to the Deep Learning algorithm group and has only barely begun to be explored. The network is an architecture for image classification, with superior performance for classification of the MNIST dataset. CapsNets have not been explored beyond image classification. This thesis introduces the use of CapsNet for Q-Learning based game algorithms. To successfully apply CapsNet in advanced game play, three main contributions follow. First, the introduction of four new game environments as frameworks for RL research with increasing complexity, namely Flash RL, Deep Line Wars, Deep RTS, and Deep Maze. These environments fill the gap between relatively simple and more complex game environments available for RL research and are in the thesis used to test and explore the CapsNet behavior. Second, the thesis introduces a generative modeling approach to produce artificial training data for use in Deep Learning models including CapsNets. We empirically show that conditional generative modeling can successfully generate game data of sufficient quality to train a Deep Q-Network well. Third, we show that CapsNet is a reliable architecture for Deep Q-Learning based algorithms for game AI. A capsule is a group of neurons that determine the presence of objects in the data and is in the literature shown to increase the robustness of training and predictions while lowering the amount training data needed. It should, therefore, be ideally suited for game plays.

Advances in deep reinforcement learning have allowed autonomous agents to perform well on Atari games, often outperforming humans, using only raw pixels to make their decisions. However, most of these games take place in 2D environments that are fully observable to the agent. In this paper, we present the first architecture to tackle 3D environments in first-person shooter games, that involve partially observable states. Typically, deep reinforcement learning methods only utilize visual input for training. We present a method to augment these models to exploit game feature information such as the presence of enemies or items, during the training phase. Our model is trained to simultaneously learn these features along with minimizing a Q-learning objective, which is shown to dramatically improve the training speed and performance of our agent. Our architecture is also modularized to allow different models to be independently trained for different phases of the game. We show that the proposed architecture substantially outperforms built-in AI agents of the game as well as average humans in deathmatch scenarios.

I got the chance to read this paper on Distributional Bellman published by DeepMind in July. Glossing over it the first time, my impression was that it would be an important paper, since the theory was sound and the experimental results were promising. However, it did not generate as much noise in the reinforcement learning community as I would have hoped. Nevertheless, as I thought the idea of Distributional Bellman was pretty neat, I decided to implement it (in Keras) and test it out myself. I hope this article can help interested readers better understanding the core concepts of Distributional Bellman. To understand Distributional Bellman, we first have to acquire a basic understanding of Q Learning.

This paper presents the first deep reinforcement learning (DRL) framework to estimate the optimal Dynamic Treatment Regimes from observational medical data. This framework is more flexible and adaptive for high dimensional action and state spaces than existing reinforcement learning methods to model real-life complexity in heterogeneous disease progression and treatment choices, with the goal of providing doctor and patients the data-driven personalized decision recommendations. The proposed DRL framework comprises (i) a supervised learning step to predict the most possible expert actions, and (ii) a deep reinforcement learning step to estimate the long-term value function of Dynamic Treatment Regimes. Both steps depend on deep neural networks. As a key motivational example, we have implemented the proposed framework on a data set from the Center for International Bone Marrow Transplant Research (CIBMTR) registry database, focusing on the sequence of prevention and treatments for acute and chronic graft versus host disease after transplantation. In the experimental results, we have demonstrated promising accuracy in predicting human experts' decisions, as well as the high expected reward function in the DRL-based dynamic treatment regimes.

In this paper, we present our approach to solve a physics-based reinforcement learning challenge "Learning to Run" with objective to train physiologically-based human model to navigate a complex obstacle course as quickly as possible. The environment is computationally expensive, has a high-dimensional continuous action space and is stochastic. We benchmark state of the art policy-gradient methods and test several improvements, such as layer normalization, parameter noise, action and state reflecting, to stabilize training and improve its sample-efficiency. We found that the Deep Deterministic Policy Gradient method is the most efficient method for this environment and the improvements we have introduced help to stabilize training. Learned models are able to generalize to new physical scenarios, e.g. different obstacle courses.

This nascent AI technique – which requires no input data, substantially less computing power, and in which the evolutionary-like AI learns from itself – could soon evolve to enable its application to real-world problems in the natural sciences. Collaboration with Earth scientists to identify the systems – from climate science, materials science, biology, and other areas – which can be codified to apply reinforcement learning for scientific progress and discovery is vital. For example, DeepMind co-founder, Demis Hassabis, has suggested that in materials science, a descendant of AlphaGo Zero could be used to search for a room temperature superconductor – a hypothetical substance that allows for incredibly efficient energy systems.

Reinforcement learning has traditionally occupied a niche status in the world of artificial intelligence. But reinforcement learning has started to assume a larger role in many AI initiatives in the past few years. Its application sweet spot is in calculation of optimal actions to be taken by agents in environmentally contextualized decision scenarios. Using trial-and-error approaches to maximize an algorithmic reward function, reinforcement learning is well suited to many adaptive-control and multiagent automation applications in IT operations management, energy, health care, commerce, finance, transportation, and finance. And it's being used to train the AI that powers both its traditional focus areas--robotics, gaming, and simulation--and a new generation of AI solutions in edge analytics, natural language processing, machine translation, computer vision, and digital assistants.