Many real-world applications require artificial agents to compete and coordinate with other agents in complex environments. As a stepping stone to this goal, the domain of StarCraft has emerged as an important challenge for artificial intelligence research, owing to its iconic and enduring status among the most difficult professional esports and its relevance to the real world in terms of its raw complexity and multi-agent challenges. Over the course of a decade and numerous competitions1-3, the strongest agents have simplified important aspects of the game, utilized superhuman capabilities, or employed hand-crafted sub-systems4. Despite these advantages, no previous agent has come close to matching the overall skill of top StarCraft players. We chose to address the challenge of StarCraft using general-purpose learning methods that are in principle applicable to other complex domains: a multi-agent reinforcement learning algorithm that uses data from both human and agent games within a diverse league of continually adapting strategies and counter-strategies, each represented by deep neural networks5,6. We evaluated our agent, AlphaStar, in the full game of StarCraft II, through a series of online games against human players. AlphaStar was rated at Grandmaster level for all three StarCraft races and above 99.8% of officially ranked human players.

Grandmaster level in StarCraft II using multi-agent reinforcement learning.

We give an overview of recent exciting achievements of deep reinforcement learning (RL). We discuss six core elements, six important mechanisms, and twelve applications. We start with background of machine learning, deep learning and reinforcement learning. Next we discuss core RL elements, including value function, in particular, Deep Q-Network (DQN), policy, reward, model, planning, and exploration. After that, we discuss important mechanisms for RL, including attention and memory, unsupervised learning, transfer learning, multi-agent RL, hierarchical RL, and learning to learn. Then we discuss various applications of RL, including games, in particular, AlphaGo, robotics, natural language processing, including dialogue systems, machine translation, and text generation, computer vision, neural architecture design, business management, finance, healthcare, Industry 4.0, smart grid, intelligent transportation systems, and computer systems. We mention topics not reviewed yet, and list a collection of RL resources. After presenting a brief summary, we close with discussions. 
Please see Deep Reinforcement Learning, arXiv:1810.06339, for a significant update.

Deep Reinforcement Learning: An Overview

This paper introduces SC2LE (StarCraft II Learning Environment), a reinforcement learning environment based on the StarCraft II game. This domain poses a new grand challenge for reinforcement learning, representing a more difficult class of problems than considered in most prior work. It is a multi-agent problem with multiple players interacting; there is imperfect information due to a partially observed map; it has a large action space involving the selection and control of hundreds of units; it has a large state space that must be observed solely from raw input feature planes; and it has delayed credit assignment requiring long-term strategies over thousands of steps. We describe the observation, action, and reward specification for the StarCraft II domain and provide an open source Python-based interface for communicating with the game engine. In addition to the main game maps, we provide a suite of mini-games focusing on different elements of StarCraft II gameplay. For the main game maps, we also provide an accompanying dataset of game replay data from human expert players. We give initial baseline results for neural networks trained from this data to predict game outcomes and player actions. Finally, we present initial baseline results for canonical deep reinforcement learning agents applied to the StarCraft II domain. On the mini-games, these agents learn to achieve a level of play that is comparable to a novice player. However, when trained on the main game, these agents are unable to make significant progress. Thus, SC2LE offers a new and challenging environment for exploring deep reinforcement learning algorithms and architectures.

StarCraft II: A New Challenge for Reinforcement Learning

As a fundamental and critical task in various visual applications, image matching can identify then correspond the same or similar structure/content from two or more images. Over the past decades, growing amount and diversity of methods have been proposed for image matching, particularly with the development of deep learning techniques over the recent years. However, it may leave several open questions about which method would be a suitable choice for specific applications with respect to different scenarios and task requirements and how to design better image matching methods with superior performance in accuracy, robustness and efficiency. This encourages us to conduct a comprehensive and systematic review and analysis for those classical and latest techniques. Following the feature-based image matching pipeline, we first introduce feature detection, description, and matching techniques from handcrafted methods to trainable ones and provide an analysis of the development of these methods in theory and practice. Secondly, we briefly introduce several typical image matching-based applications for a comprehensive understanding of the significance of image matching. In addition, we also provide a comprehensive and objective comparison of these classical and latest techniques through extensive experiments on representative datasets. Finally, we conclude with the current status of image matching technologies and deliver insightful discussions and prospects for future works. This survey can serve as a reference for (but not limited to) researchers and engineers in image matching and related fields.

/pdf/image-matching-from-handcrafted-to-deep-features-a-survey-27kn6w026w.pdf

Image Matching from Handcrafted to Deep Features: A Survey

Seeking reliable correspondences between two feature sets is a fundamental and important task in computer vision. This paper attempts to remove mismatches from given putative image feature correspondences. To achieve the goal, an efficient approach, termed as locality preserving matching (LPM), is designed, the principle of which is to maintain the local neighborhood structures of those potential true matches. We formulate the problem into a mathematical model, and derive a closed-form solution with linearithmic time and linear space complexities. Our method can accomplish the mismatch removal from thousands of putative correspondences in only a few milliseconds. To demonstrate the generality of our strategy for handling image matching problems, extensive experiments on various real image pairs for general feature matching, as well as for point set registration, visual homing and near-duplicate image retrieval are conducted. Compared with other state-of-the-art alternatives, our LPM achieves better or favorably competitive performance in accuracy while intensively cutting time cost by more than two orders of magnitude.

Locality Preserving Matching

This paper presents an overview of the existing work on AI for real-time strategy (RTS) games. Specifically, we focus on the work around the game StarCraft, which has emerged in the past few years as the unified test bed for this research. We describe the specific AI challenges posed by RTS games, and overview the solutions that have been explored to address them. Additionally, we also present a summary of the results of the recent StarCraft AI competitions, describing the architectures used by the participants. Finally, we conclude with a discussion emphasizing which problems in the context of RTS game AI have been solved, and which remain open.

/pdf/a-survey-of-real-time-strategy-game-ai-research-and-obid322jza.pdf

A Survey of Real-Time Strategy Game AI Research and Competition in StarCraft

Heuristic search has been very successful in abstract game domains such as Chess and Go. In video games, however, adoption has been slow due to the fact that state and move spaces are much larger, real-time constraints are harsher, and constraints on computational resources are tighter. In this paper we present a fast search method — Alpha-Beta search for durative moves — that can defeat commonly used AI scripts in RTS game combat scenarios of up to 8 vs. 8 units running on a single core in under 5ms per search episode. This performance is achieved by using standard search enhancements such as transposition tables and iterative deepening, and novel usage of combat AI scripts for sorting moves and state evaluation via playouts. We also present evidence that commonly used combat scripts are highly exploitable — opening the door for a promising line of research on opponent combat modelling.

/pdf/fast-heuristic-search-for-rts-game-combat-scenarios-3wjn4seboj.pdf

Fast heuristic search for RTS game combat scenarios

Real-time strategy video games have proven to be a very challenging area for applications of artificial intelligence research. With their vast state and action spaces and real-time constraints, existing AI solutions have been shown to be too slow, or only able to be applied to small problem sets, while human players still dominate RTS AI systems. This paper makes three contributions to advancing the state of AI for popular commercial RTS game combat, which can consist of battles of dozens of units. First, we present an efficient system for modelling abstract RTS combat called SparCraft, which can perform millions of unit actions per second and visualize them. We then present a modification of the UCT algorithm capable of performing search in games with simultaneous and durative actions. Finally, a novel greedy search algorithm called Portfolio Greedy Search is presented which uses hill climbing and accurate playout-based evaluations to efficiently search even the largest combat scenarios. We demonstrate that Portfolio Greedy Search outperforms state of the art Alpha-Beta and UCT search methods for large StarCraft combat scenarios of up to 50 vs. 50 units under real-time search constraints of 40 ms per search episode.

Portfolio greedy search and simulation for large-scale combat in starcraft

In recent years, real-time strategy (RTS) games have gained interest in the AI research community for their multitude of challenging subproblems — such as collaborative pathfinding, effective resource allocation and unit targeting, to name a few. In this paper we consider the build order problem in RTS games in which we need to find concurrent action sequences that, constrained by unit dependencies and resource availability, create a certain number of units and structures in the shortest possible time span. We present abstractions and heuristics that speed up the search for approximative solutions considerably in the game of StarCraft, and show the efficacy of our method by comparing its real-time performance with that of professional StarCraft players.

/pdf/build-order-optimization-in-starcraft-31en5drwy0.pdf

Build order optimization in StarCraft

In recent years, real-time strategy (RTS) games have gained attention in the AI research community for their multitude of challenging and relevant real-time decision problems that have to be solved in order to win against human experts or to effectively collaborate with other players in team-games In this article we motivate research in this area, give an overview of past RTS game AI competitions, and discuss future directions

/pdf/real-time-strategy-game-competitions-3oxj53jfyh.pdf

David Churchill

Papers

A Survey of Real-Time Strategy Game AI Research and Competition in StarCraft

Fast heuristic search for RTS game combat scenarios

Portfolio greedy search and simulation for large-scale combat in starcraft

Build order optimization in StarCraft

Real-Time Strategy Game Competitions