This paper presents Knowledge-Based Reinforcement Learning (KB-RL) as a method that combines a knowledge-based approach and a reinforcement learning (RL) technique into one method for intelligent problem solving. The proposed approach focuses on multi-expert knowledge acquisition, with the reinforcement learning being applied as a conflict resolution strategy aimed at integrating the knowledge of multiple exerts into one knowledge base.
The article describes the KB-RL approach in detail and applies the reported method to one of the most challenging problems of current Artificial Intelligence (AI) research, namely playing a strategy game. The results show that the KB-RL system is able to play and complete the full FreeCiv game, and to win against the computer players in various game settings. Moreover, with more games played, the system improves the gameplay by shortening the number of rounds that it takes to win the game.
Overall, the reported experiment supports the idea that, based on human knowledge and empowered by reinforcement learning, the KB-RL system can deliver a strong solution to the complex, multi-strategic problems, and, mainly, to improve the solution with increased experience.
Artificial Intelligence is becoming instrumental in a variety of applications. Games serve as a good breeding ground for trying and testing these algorithms in a sandbox with simpler constraints in comparison to real life. In this project, we aim to develop an AI agent that can solve the classical Japanese game of Sokoban using various algorithms and heuristics and compare their performances through standard metrics.
The game of 2048 is a highly addictive game. It is easy to learn the game, but hard to master as the created game revealed that only about 1% games out of hundreds million ever played have been won. In this paper, we would like to explore reinforcement learning techniques to win 2048. The approaches we have took include deep Q-learning and beam search, with beam search reaching 2048 28.5 of time.
Southern University of Science and Technology（南方科技大学）；University of Birmingham（伯明翰大学）；New York University（纽约大学）
Reinforcement learning algorithms have performed well in playing challenging board and video games. More and more studies focus on improving the generalisation ability of reinforcement learning algorithms. The General Video Game AI Learning Competition aims to develop agents capable of learning to play different game levels that were unseen during training. This paper summarises the five years' General Video Game AI Learning Competition editions. At each edition, three new games were designed. The training and test levels were designed separately in the first three editions. Since 2020, three …
Leiden Institute of Advanced Computer Science, Leiden University（莱顿大学莱顿高等计算机科学研究所）；Leiden University（莱顿大学）；Leiden Institute of Advanced Computer Science（莱顿高等计算机科学研究所）；Leiden University, Leiden, the Netherlands（莱顿大学，荷兰莱顿）
After the recent groundbreaking results of AlphaGo, we have seen a strong interest in reinforcement learning in game playing. General Game Playing (GGP) provides a good testbed for reinforcement learning. In GGP, a specification of games rules is given. GGP problems can be solved by reinforcement learning. Q-learning is one of the canonical reinforcement learning methods, and has been used by (Banerjee & Stone, IJCAI 2007) in GGP. In this paper we implement Q-learning in GGP for three small-board games (Tic-Tac-Toe, Connect Four, Hex), to allow comparison to Banerjee et al. As expected, Q-lear…
Federal University of ABC（ABC联邦大学）；Vrije Universiteit Amsterdam（阿姆斯特丹自由大学）；Heriot-Watt University（赫瑞-瓦特大学）
This paper describes a competition proposal for evolving Intelligent Agents for the game-playing framework called EvoMan. The framework is based on the boss fights of the game called Mega Man II developed by Capcom. For this particular competition, the main goal is to beat all of the eight bosses using a generalist strategy. In other words, the competitors should train the agent to beat a set of the bosses and then the agent will be evaluated by its performance against all eight bosses. At the end of this paper, the competitors are provided with baseline results so that they can have an intuit…
Leiden University（莱顿大学）；Leiden Institute of Advanced Computer Science（莱顿高级计算机科学研究所）
After the recent groundbreaking results of AlphaGo and AlphaZero, we have seen strong interests in deep reinforcement learning and artificial general intelligence (AGI) in game playing. However, deep learning is resource-intensive and the theory is not yet well developed. For small games, simple classical table-based Q-learning might still be the algorithm of choice. General Game Playing (GGP) provides a good testbed for reinforcement learning to research AGI. Q-learning is one of the canonical reinforcement learning methods, and has been used by (Banerjee $\&$ Stone, IJCAI 2007) in GGP. In th…
Recently, multiple approaches for creating agents for playing various complex real-time computer games such as StarCraft II or Dota 2 were proposed, however, they either embed a significant amount of expert knowledge into the agent or use a prohibitively large for most researchers amount of computational resources. We propose a neural network architecture for playing the full two-player match of StarCraft II trained with general-purpose supervised and reinforcement learning, that can be trained on a single consumer-grade PC with a single GPU. We also show that our implementation achieves a non…
Queen Mary University of London（伦敦玛丽女王大学）；Southern University of Science and Technology（南方科技大学）
The General Video Game AI competitions have been the testing ground for several techniques for game playing, such as evolutionary computation techniques, tree search algorithms, hyper heuristic based or knowledge based algorithms. So far the metrics used to evaluate the performance of agents have been win ratio, game score and length of games. In this paper we provide a wider set of metrics and a comparison method for evaluating and comparing agents. The metrics and the comparison method give shallow introspection into the agent's decision making process and they can be applied to any agent re…
This paper introduces a novel method for learning how to play the most difficult Atari 2600 games from the Arcade Learning Environment using deep reinforcement learning. The proposed method, human checkpoint replay, consists in using checkpoints sampled from human gameplay as starting points for the learning process. This is meant to compensate for the difficulties of current exploration strategies, such as epsilon-greedy, to find successful control policies in games with sparse rewards. Like other deep reinforcement learning architectures, our model uses a convolutional neural network that re…
Maynooth University（梅努斯大学）；National Autonomous University of Mexico（墨西哥国立自治大学）
Monte Carlo Tree Search (MCTS) is a relatively new sampling method with multiple variants in the literature. They can be applied to a wide variety of challenging domains including board games, video games, and energy-based problems to mention a few. In this work, we explore the use of the vanilla MCTS and the MCTS with Rapid Action Value Estimation (MCTS-RAVE) in the game of Carcassonne, a stochastic game with a deceptive scoring system where limited research has been conducted. We compare the strengths of the MCTS-based methods with the Star2.5 algorithm, previously reported to yield competit…
Queen Mary University of London（伦敦玛丽女王大学）；Leibniz University Hannover（汉诺威莱布尼茨大学）
Strategy video games challenge AI agents with their combinatorial search space caused by complex game elements. State abstraction is a popular technique that reduces the state space complexity. However, current state abstraction methods for games depend on domain knowledge, making their application to new games expensive. State abstraction methods that require no domain knowledge are studied extensively in the planning domain. However, no evidence shows they scale well with the complexity of strategy games. In this paper, we propose Elastic MCTS, an algorithm that uses state abstraction to pla…
The General Video Game Artificial Intelligence (GVGAI) competition has been running for several years with various tracks. This paper focuses on the challenge of the GVGAI learning track in which 3 games are selected and 2 levels are given for training, while 3 hidden levels are left for evaluation. This setup poses a difficult challenge for current Reinforcement Learning (RL) algorithms, as they typically require much more data. This work investigates 3 versions of the Advantage Actor-Critic (A2C) algorithm trained on a maximum of 2 levels from the available 5 from the GVGAI framework and com…
Human beings are particularly good at reasoning and inference from just a few examples. When facing new tasks, humans will leverage knowledge and skills learned before, and quickly integrate them with the new task. In addition to learning by experimentation, human also learn socio-culturally through instructions and learning by example. In this way humans can learn much faster compared with most current artificial intelligence algorithms in many tasks. In this paper, we test the idea of speeding up machine learning through social learning. We argue that in solving real-world problems, especial…
We investigate systematically the impact of human intervention in the training of computer players in a strategy board game. In that game, computer players utilise reinforcement learning with neural networks for evolving their playing strategies and demonstrate a slow learning speed. Human intervention can significantly enhance learning performance, but carry-ing it out systematically seems to be more of a problem of an integrated game development environment as opposed to automatic evolutionary learning.
We present a new dataset containing 10K human-annotated games of Go and show how these natural language annotations can be used as a tool for model interpretability. Given a board state and its associated comment, our approach uses linear probing to predict mentions of domain-specific terms (e.g., ko, atari) from the intermediate state representations of game-playing agents like AlphaGo Zero. We find these game concepts are nontrivially encoded in two distinct policy networks, one trained via imitation learning and another trained via reinforcement learning. Furthermore, mentions of domain-spe…
Computer Science Institute TH K \"o ln -- Cologne University of Applied Sciences Gummersbach, Germany
We present a new general board game (GBG) playing and learning framework. GBG defines the common interfaces for board games, game states and their AI agents. It allows one to run competitions of different agents on different games. It standardizes those parts of board game playing and learning that otherwise would be tedious and repetitive parts in coding. GBG is suitable for arbitrary 1-, 2-, ..., N-player board games. It makes a generic TD($λ$)-n-tuple agent for the first time available to arbitrary games. On various games, TD($λ$)-n-tuple is found to be superior to other generic agents like…
Tencent AI Lab（腾讯人工智能实验室）；Tencent TiMi L1 Studio（腾讯天美L1工作室）
MOBA games, e.g., Honor of Kings, League of Legends, and Dota 2, pose grand challenges to AI systems such as multi-agent, enormous state-action space, complex action control, etc. Developing AI for playing MOBA games has raised much attention accordingly. However, existing work falls short in handling the raw game complexity caused by the explosion of agent combinations, i.e., lineups, when expanding the hero pool in case that OpenAI's Dota AI limits the play to a pool of only 17 heroes. As a result, full MOBA games without restrictions are far from being mastered by any existing AI system. In…
Deep reinforcement learning has shown its success in game playing. However, 2.5D fighting games would be a challenging task to handle due to ambiguity in visual appearances like height or depth of the characters. Moreover, actions in such games typically involve particular sequential action orders, which also makes the network design very difficult. Based on the network of Asynchronous Advantage Actor-Critic (A3C), we create an OpenAI-gym-like gaming environment with the game of Little Fighter 2 (LF2), and present a novel A3C+ network for learning RL agents. The introduced model includes a Rec…
Mastering a video game requires skill, tactics and strategy. While these attributes may be acquired naturally by human players, teaching them to a computer program is a far more challenging task. In recent years, extensive research was carried out in the field of reinforcement learning and numerous algorithms were introduced, aiming to learn how to perform human tasks such as playing video games. As a result, the Arcade Learning Environment (ALE) (Bellemare et al., 2013) has become a commonly used benchmark environment allowing algorithms to train on various Atari 2600 games. In many games the…
School of Computer Science（计算机科学学院）；Carnegie Mellon University（卡内基梅隆大学）
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 …
IBM Research（IBM研究院）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）
Interactive Fiction (IF) games with real human-written natural language texts provide a new natural evaluation for language understanding techniques. In contrast to previous text games with mostly synthetic texts, IF games pose language understanding challenges on the human-written textual descriptions of diverse and sophisticated game worlds and language generation challenges on the action command generation from less restricted combinatorial space. We take a novel perspective of IF game solving and re-formulate it as Multi-Passage Reading Comprehension (MPRC) tasks. Our approaches utilize th…
This paper discusses the effects of social learning in training of game playing agents. The training of agents in a social context instead of a self-play environment is investigated. Agents that use the reinforcement learning algorithms are trained in social settings. This mimics the way in which players of board games such as scrabble and chess mentor each other in their clubs. A Round Robin tournament and a modified Swiss tournament setting are used for the training. The agents trained using social settings are compared to self play agents and results indicate that more robust agents emerge …
Text based games are simulations in which an agent interacts with the world purely through natural language. They typically consist of a number of puzzles interspersed with interactions with common everyday objects and locations. Deep reinforcement learning agents can learn to solve these puzzles. However, the everyday interactions with the environment, while trivial for human players, present as additional puzzles to agents. We explore two techniques for incorporating commonsense knowledge into agents. Inferring possibly hidden aspects of the world state with either a commonsense inference mo…
The game of Go has a long history in East Asian countries, but the field of Computer Go has yet to catch up to humans until the past couple of years. While the rules of Go are simple, the strategy and combinatorics of the game are immensely complex. Even within the past couple of years, new programs that rely on neural networks to evaluate board positions still explore many orders of magnitude more board positions per second than a professional can. We attempt to mimic human intuition in the game by creating a convolutional neural policy network which, without any sort of tree search, should p…
A general approach to knowledge transfer is introduced in which an agent controlled by a neural network adapts how it reuses existing networks as it learns in a new domain. Networks trained for a new domain can improve their performance by routing activation selectively through previously learned neural structure, regardless of how or for what it was learned. A neuroevolution implementation of this approach is presented with application to high-dimensional sequential decision-making domains. This approach is more general than previous approaches to neural transfer for reinforcement learning. I…
INESC-ID（INESC-ID（葡萄牙国家系统与计算机工程研究所））；Instituto Superior Técnico, University of Lisbon（里斯本大学高等理工学院）；Carnegie Mellon University（卡内基梅隆大学）
In this work we explore the use of latent representations obtained from multiple input sensory modalities (such as images or sounds) in allowing an agent to learn and exploit policies over different subsets of input modalities. We propose a three-stage architecture that allows a reinforcement learning agent trained over a given sensory modality, to execute its task on a different sensory modality-for example, learning a visual policy over image inputs, and then execute such policy when only sound inputs are available. We show that the generalized policies achieve better out-of-the-box performa…
School of Interactive Computing（交互式计算学院）；Georgia Institute of Technology（佐治亚理工学院）
Text-based adventure games provide a platform on which to explore reinforcement learning in the context of a combinatorial action space, such as natural language. We present a deep reinforcement learning architecture that represents the game state as a knowledge graph which is learned during exploration. This graph is used to prune the action space, enabling more efficient exploration. The question of which action to take can be reduced to a question-answering task, a form of transfer learning that pre-trains certain parts of our architecture. In experiments using the TextWorld framework, we s…
The University of Tokyo Hospital（东京大学医院）；The University of Tokyo（东京大学）
The Werewolf game is a social deduction game based on free natural language communication, in which players try to deceive others in order to survive. An important feature of this game is that a large portion of the conversations are false information, and the behavior of artificial intelligence (AI) in such a situation has not been widely investigated. The purpose of this study is to develop an AI agent that can play Werewolf through natural language conversations. First, we collected game logs from 15 human players. Next, we fine-tuned a Transformer-based pretrained language model to constru…
In the last decade, deep learning has achieved great success in machine learning tasks where the input data is represented with different levels of abstractions. Driven by the recent research in reinforcement learning using deep neural networks, we explore the feasibility of designing a learning model based on expert behaviour for complex, multidimensional tasks where reward function is not available. We propose a novel method for apprenticeship learning based on the previous research on supervised learning techniques in reinforcement learning. Our method is applied to video frames from Atari …
Deep reinforcement learning methods traditionally struggle with tasks where environment rewards are particularly sparse. One successful method of guiding exploration in these domains is to imitate trajectories provided by a human demonstrator. However, these demonstrations are typically collected under artificial conditions, i.e. with access to the agent's exact environment setup and the demonstrator's action and reward trajectories. Here we propose a two-stage method that overcomes these limitations by relying on noisy, unaligned footage without access to such data. First, we learn to map una…
While games have been used extensively as milestones to evaluate game-playing AI, there exists no standardised framework for reporting the obtained observations. As a result, it remains difficult to draw general conclusions about the strengths and weaknesses of different game-playing AI algorithms. In this paper, we propose reporting guidelines for AI game-playing performance that, if followed, provide information suitable for unbiased comparisons between different AI approaches. The vision we describe is to build benchmarks and competitions based on such guidelines in order to be able to draw…
IT University of Copenhagen（哥本哈根信息技术大学）；New York University（纽约大学）
In this article, we review recent Deep Learning advances in the context of how they have been applied to play different types of video games such as first-person shooters, arcade games, and real-time strategy games. We analyze the unique requirements that different game genres pose to a deep learning system and highlight important open challenges in the context of applying these machine learning methods to video games, such as general game playing, dealing with extremely large decision spaces and sparse rewards.
Queen Mary University of London（伦敦玛丽女王大学）；Southern University of Science and Technology（南方科技大学）
Game-based benchmarks have been playing an essential role in the development of Artificial Intelligence (AI) techniques. Providing diverse challenges is crucial to push research toward innovation and understanding in modern techniques. Rinascimento provides a parameterised partially-observable multiplayer card-based board game, these parameters can easily modify the rules, objectives and items in the game. We describe the framework in all its features and the game-playing challenge providing baseline game-playing AIs and analysis of their skills. We reserve to agents' hyper-parameter tuning a …
Monte Carlo Tree Search techniques have generally dominated General Video Game Playing, but recent research has started looking at Evolutionary Algorithms and their potential at matching Tree Search level of play or even outperforming these methods. Online or Rolling Horizon Evolution is one of the options available to evolve sequences of actions for planning in General Video Game Playing, but no research has been done up to date that explores the capabilities of the vanilla version of this algorithm in multiple games. This study aims to critically analyse the different configurations regardin…
Maastricht University（马斯特里赫特大学）；Facebook AI Research（Facebook AI研究院）
Combinations of Monte-Carlo tree search and Deep Neural Networks, trained through self-play, have produced state-of-the-art results for automated game-playing in many board games. The training and search algorithms are not game-specific, but every individual game that these approaches are applied to still requires domain knowledge for the implementation of the game's rules, and constructing the neural network's architecture -- in particular the shapes of its input and output tensors. Ludii is a general game system that already contains over 500 different games, which can rapidly grow thanks to…
Portfolio methods represent a simple but efficient type of action abstraction which has shown to improve the performance of search-based agents in a range of strategy games. We first review existing portfolio techniques and propose a new algorithm for optimization and action-selection based on the Rolling Horizon Evolutionary Algorithm. Moreover, a series of variants are developed to solve problems in different aspects. We further analyze the performance of discussed agents in a general strategy game-playing task. For this purpose, we run experiments on three different game-modes of the Strate…
University of Wrocław（弗罗茨瓦夫大学）；Poland（波兰（注：原文本中“Poland”为国家名，此处按要求提取机构，原“University of Wrocław”已包含机构核心，“Poland”为国家，非机构，可能为原文本排版问题，正确机构仅“University of Wrocław”）}]，修正后应为：{）
We describe nearly fifteen years of General Game Playing experimental research history in the context of reproducibility and fairness of comparisons between various GGP agents and systems designed to play games described by different formalisms. We think our survey may provide an interesting perspective of how chaotic methods were allowed when nothing better was possible. Finally, from our experience-based view, we would like to propose a few recommendations of how such specific heterogeneous branch of research should be handled appropriately in the future. The goal of this note is to point ou…
New York University（纽约大学）；University of Hertfordshire（赫特福德大学）；University of Southern California（南加利福尼亚大学）
From the beginning if the history of AI, there has been interest in games as a platform of research. As the field developed, human-level competence in complex games became a target researchers worked to reach. Only relatively recently has this target been finally met for traditional tabletop games such as Backgammon, Chess and Go. Current research focus has shifted to electronic games, which provide unique challenges. As is often the case with AI research, these results are liable to be exaggerated or misrepresented by either authors or third parties. The extent to which these games benchmark …
In the realm of games research, Artificial General Intelligence algorithms often use score as main reward signal for learning or playing actions. However this has shown its severe limitations when the point rewards are very rare or absent until the end of the game. This paper proposes a new approach based on event logging: the game state triggers an event every time one of its features changes. These events are processed by an Event-value Function (EF) that assigns a value to a single action or a sequence. The experiments have shown that such approach can mitigate the problem of scarce point r…
National Institute for Mathematical Sciences（韩国数学科学研究所）
Deep learning technology is making great progress in solving the challenging problems of artificial intelligence, hence machine learning based on artificial neural networks is in the spotlight again. In some areas, artificial intelligence based on deep learning is beyond human capabilities. It seemed extremely difficult for a machine to beat a human in a Go game, but AlphaGo has shown to beat a professional player in the game. By looking at the statistical distribution of the distance in which the Go stones are laid in succession, we find a clear trace that Alphago has surpassed human abilitie…
University of Strathclyde（思克莱德大学）；Queen Mary University of London（伦敦玛丽女王大学）
Ensemble Decision Systems offer a unique form of decision making that allows a collection of algorithms to reason together about a problem. Each individual algorithm has its own inherent strengths and weaknesses, and often it is difficult to overcome the weaknesses while retaining the strengths. Instead of altering the properties of the algorithm, the Ensemble Decision System augments the performance with other algorithms that have complementing strengths. This work outlines different options for building an Ensemble Decision System as well as providing analysis on its performance compared to …
Tsinghua University（清华大学）；National University of Defense Technology（国防科技大学）；RealAI（瑞莱智慧）；Tencent AI Lab（腾讯人工智能实验室）
Deep reinforcement learning (DRL) has achieved super-human performance on complex video games (e.g., StarCraft II and Dota II). However, current DRL systems still suffer from challenges of multi-agent coordination, sparse rewards, stochastic environments, etc. In seeking to address these challenges, we employ a football video game, e.g., Google Research Football (GRF), as our testbed and develop an end-to-end learning-based AI system (denoted as TiKick) to complete this challenging task. In this work, we first generated a large replay dataset from the self-playing of single-agent experts, whic…
