The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Everyone is familiar with the scenario, people demand or assign tasks to robots, and robots execute the tasks to serve people. We call such a model Serve-on-Demand. With the advancement of pervasive computing, machine learning and artificial intelligence, the robot service of the next generation will inevitably turn to actively and exactly meet people's needs, even without explicit demand. We call...
As a famous game in the domain of game theory, both pervasive empirical studies as well as intensive theoretical analysis have been conducted and performed worldwide to research different public goods game scenarios. At the same time, computer game simulators are utilized widely for better research of game theory by providing easy but powerful visualization and statistics functionalities. However,...
We consider the issue of segmenting an action in the learning phase into a logical set of smaller primitives in order to construct a generative model for imitation learning using a hierarchical approach. Our proposed framework, addressing the “how-to” question in imitation, is based on a one-shot imitation learning algorithm. It incorporates segmentation of a demonstrated template into a series of...
This paper deals with the problem of multi-agent learning of a population of players, engaged in a repeated normal-form game. Assuming boundedly-rational agents, we propose a model of social learning based on trial and error, called “social reinforcement learning”. This extension of well-known Q-learning algorithm, allows players within a population to communicate and share their experiences with...
Game Based Personality Profiling Application had been develop as an application to solve the problems faced by a counselor in capturing and determine personality. There are many types of personality model and theory such as Jung's Sixteen personality, Myers Briggs Types Indicators (MBTI), 5 Big factors, and Kathrine Benziger's Personality. This application uses MBTI based concept as a guideline to...
The criterion of fairness has not been given much attention in the research of multi-agent learning problem. We propose an adaptive strategy for agents to achieve fairness in repeated two-agent game with conflicting interests. In our strategy, each agent is equipped with inequity-averse based fairness model, and makes its decision according to its attractiveness for each action. Besides, each agent...
At the heart of multi-robot task allocation lies the ability to compare multiple options in order to select the best. In some domains this utility evaluation is not straightforward, for example due to complex and unmodeled underlying dynamics or an adversary in the environment. Explicitly modeling these extrinsic influences well enough so that they can be accounted for in utility computation (and...
This paper uses genetic programming (GP) to evolve a variety of reactive agents for a simulated version of the classic arcade game Ms. Pac-Man. A diverse set of behaviours were evolved using the same GP setup in three different versions of the game. The results show that GP is able to evolve controllers that are well-matched to the game used for evolution and, in some cases, also generalise well to...
In virtual worlds, character credibility suffers from an increasing discrepancy between visual realism, physical modelling quality and behaviour simulation weakness. As behaviour credibility is firmly embedded in the eye of the human observer, it needs to be as close to human expectation as possible. In this study, we define a learning process able to build rule-based behaviour from the observation...
We propose a robust approach for learning car racing track models from sensory data for the car racing simulator TORCS. Our track recognition system is based on the combination of an advanced preprocessing step of the sensory data and a simple classifier that delivers six types of track shapes similar to the ones a human would recognize. Out of these, establishing a complete track model is straightforward...
There has been growing interest in creating intelligent agents in virtual worlds that do not follow fixed scripts predefined by the developers, but react accordingly based on actions performed by human players during their interaction. In order to achieve this objective, previous approaches have attempted to model the environment and the user's context directly. However, a critical component for enabling...
In this paper we apply Coevolutionary Temporal Difference Learning (CTDL), a hybrid of coevolutionary search and reinforcement learning proposed in our former study, to evolve strategies for playing the game of Go on small boards (5×5). CTDL works by interlacing exploration of the search space provided by one-population competitive coevolution and exploitation by means of temporal difference learning...
In the paper we evaluate two learning methods applied to the ball-in-a-cup game. The first approach is based on imitation learning. The captured trajectory was encoded with Dynamic motion primitives (DMP). The DMP approach allows simple adaptation of the demonstrated trajectory to the robot dynamics. In the second approach, we use reinforcement learning, which allows learning without any previous...
Character design artists typically use shape, pose and proportion as the first design layer to express role, physicality and personality traits. Inspired by this we approach the problem of automatic character synthesis by attempting to learn relations among the body-shape, proportions, pose, and trait labels from finished art. In our prior work, we have designed an online game framework to collect...
We present a self-learning evolutionary Prisoner's Dilemma game model to study the evolution of cooperation in network-structured populations. During the evolutionary process, each agent updates its current strategy with a probability depending on the difference feedback between its actual score and score aspiration. Each agent's score is a weighed mean of its payoff coming from its neighbors (social...
In this paper, we present an approach of adaptive learning mechanism for game agents' real-time behavior control. This approach mainly focuses on how to generate game agent's adaptability in real-time. It is possible to apply our approach in complicated game character interactions by following the framework discussed in this paper. We consider the layered architecture, the behavior pattern and the...
When dealing with cognitive architecture and behavior, chunks are one of the most well known and accepted constructs. Despite that, the nature of chunks still remains very elusive, especially with understanding chunks in procedural knowledge. Our attempt is to show the existence of chunks in procedural knowledge, define them, and describe their characteristics. With this purpose in mind, we use data...
Backpropagation and neuroevolution are used in a Lamarckian evolution process to train a neural network visual controller for agents in the Quake II environment. In previous work, we hand-coded a non-visual controller for supervising in backpropagation, but hand-coding can only be done for problems with known solutions. In this research the problem for the agent is to attack a moving enemy in a visually...
The aim of General Game Playing (GGP) is to create intelligent agents that can automatically learn how to play a wide variety of different games at an expert level without any human intervention. This requires that the agents be capable of learning diverse game-playing strategies from basic game rules without any game-specific knowledge being provided by their developers. A successful realization...
This paper reports our experiment on applying Q Learning algorithm for learning to play Tic-tac-toe. The original algorithm is modified by updating the Q value only when the game terminates, propagating the update process from the final move backward to the first move, and incorporating a new update rule. We evaluate the agent performance using full-board and partial-board representations. In this...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.