Related Research Articles
Game theory is the study of mathematical models of strategic interactions among rational agents. It has applications in many fields of social science, used extensively in economics as well as in logic, systems science and computer science. Traditional game theory addressed two-person zero-sum games, in which a participant's gains or losses are exactly balanced by the losses and gains of the other participant. In the 21st century, game theory applies to a wider range of behavioral relations, and it is now an umbrella term for the science of rational decision making in humans, animals, as well as computers.
Reinforcement learning (RL) is an interdisciplinary area of machine learning and optimal control concerned with how an intelligent agent ought to take actions in a dynamic environment in order to maximize the cumulative reward. Reinforcement learning is one of three basic machine learning paradigms, alongside supervised learning and unsupervised learning.
Organization development (OD) is the study and implementation of practices, systems, and techniques that affect organizational change. The goal of which is to modify a group's/organization's performance and/or culture. The organizational changes are typically initiated by the group's stakeholders. OD emerged from human relations studies in the 1930s, during which psychologists realized that organizational structures and processes influence worker behavior and motivation.
Experimental economics is the application of experimental methods to study economic questions. Data collected in experiments are used to estimate effect size, test the validity of economic theories, and illuminate market mechanisms. Economic experiments usually use cash to motivate subjects, in order to mimic real-world incentives. Experiments are used to help understand how and why markets and other exchange systems function as they do. Experimental economics have also expanded to understand institutions and the law.
A multi-agent system is a computerized system composed of multiple interacting intelligent agents. Multi-agent systems can solve problems that are difficult or impossible for an individual agent or a monolithic system to solve. Intelligence may include methodic, functional, procedural approaches, algorithmic search or reinforcement learning.
Game balance is a branch of game design with the intention of improving gameplay and user experience by balancing difficulty and fairness. Game balance consists of adjusting rewards, challenges, and/or elements of a game to create the intended player experience.
Q-learning is a model-free reinforcement learning algorithm to learn the value of an action in a particular state. It does not require a model of the environment, and it can handle problems with stochastic transitions and rewards without requiring adaptations.
Information economics or the economics of information is the branch of microeconomics that studies how information and information systems affect an economy and economic decisions.
Computational economics is an interdisciplinary research discipline that combines methods in computational science and economics to solve complex economic problems. This subject encompasses computational modeling of economic systems. Some of these areas are unique, while others established areas of economics by allowing robust data analytics and solutions of problems that would be arduous to research without computers and associated numerical methods.
In probability theory and machine learning, the multi-armed bandit problem is a problem in which a decision maker iteratively selects one of multiple fixed choices when the properties of each choice are only partially known at the time of allocation, and may become better understood as time passes. A fundamental aspect of bandit problems is that choosing an arm does not affect the properties of the arm or other arms.
The rational planning model is a model of the planning process involving a number of rational actions or steps. Taylor (1998) outlines five steps, as follows:
Rooted in agile software development and initially referred to leading self-organizing development teams, the concept of agile leadership is now used to more generally denote an approach to people and team leadership that is focused on boosting adaptiveness in highly dynamic and complex business environments.
Active learning is a special case of machine learning in which a learning algorithm can interactively query a human user, to label new data points with the desired outputs. The human user must possess knowledge/expertise in the problem domain, including the ability to consult/research authoritative sources when necessary. In statistics literature, it is sometimes also called optimal experimental design. The information source is also called teacher or oracle.
Thompson sampling, named after William R. Thompson, is a heuristic for choosing actions that address the exploration-exploitation dilemma in the multi-armed bandit problem. It consists of choosing the action that maximizes the expected reward with respect to a randomly drawn belief.
Metalearning is a neuroscientific term proposed by Kenji Doya, as a theory for how neurotransmitters facilitate distributed learning mechanisms in the Basal Ganglia. The theory primarily involves the role of neurotransmitters in dynamically adjusting the way computational learning algorithms interact to produce the kinds of robust learning behaviour currently unique to biological life forms. 'Metalearning' has previously been applied to the fields of Social Psychology and Computer Science but in this context exists as an entirely new concept.
Deep reinforcement learning is a subfield of machine learning that combines reinforcement learning (RL) and deep learning. RL considers the problem of a computational agent learning to make decisions by trial and error. Deep RL incorporates deep learning into the solution, allowing agents to make decisions from unstructured input data without manual engineering of the state space. Deep RL algorithms are able to take in very large inputs and decide what actions to perform to optimize an objective. Deep reinforcement learning has been used for a diverse set of applications including but not limited to robotics, video games, natural language processing, computer vision, education, transportation, finance and healthcare.
Artificial intelligence and machine learning techniques are used in video games for a wide variety of applications such as non-player character (NPC) control and procedural content generation (PCG). Machine learning is a subset of artificial intelligence that uses historical data to build predictive and analytical models. This is in sharp contrast to traditional methods of artificial intelligence such as search trees and expert systems.
Multi-agent reinforcement learning (MARL) is a sub-field of reinforcement learning. It focuses on studying the behavior of multiple learning agents that coexist in a shared environment. Each agent is motivated by its own rewards, and does actions to advance its own interests; in some environments these interests are opposed to the interests of other agents, resulting in complex group dynamics.
Intrinsic motivation in the study of artificial intelligence and robotics is a mechanism for enabling artificial agents to exhibit inherently rewarding behaviours such as exploration and curiosity, grouped under the same term in the study of psychology. Psychologists consider intrinsic motivation in humans to be the drive to perform an activity for inherent satisfaction – just for the fun or challenge of it.
In machine learning, reinforcement learning from human feedback (RLHF) is a technique to align an intelligent agent to human preferences. In classical reinforcement learning, the goal of such an agent is to learn a function that guides its behavior called a policy. This function learns to maximize the reward it receives from a separate reward function based on its task performance. However, it is difficult to define explicitly a reward function that approximates human preferences. Therefore, RLHF seeks to train a "reward model" directly from human feedback. The reward model is first trained in a supervised fashion—independently from the policy being optimized—to predict if a response to a given prompt is good or bad based on ranking data collected from human annotators. This model is then used as a reward function to improve an agent's policy through an optimization algorithm like proximal policy optimization.
References
- ↑ Berger-Tal, Oded; Nathan, Jonathan; Meron, Ehud; Saltz, David (22 April 2014). "The Exploration-Exploitation Dilemma: A Multidisciplinary Framework". PLOS ONE. 9 (4): e95693. Bibcode:2014PLoSO...995693B. doi: 10.1371/journal.pone.0095693 . PMC 3995763 . PMID 24756026.
- ↑ Rhee, Mooweon; Kim, Tohyun (2018). "Exploration and Exploitation". The Palgrave Encyclopedia of Strategic Management. London: Palgrave Macmillan UK. pp. 543–546. doi:10.1057/978-1-137-00772-8_388. ISBN 978-0-230-53721-7.
- ↑ Fruit, R. (2019). Exploration-exploitation dilemma in Reinforcement Learning under various form of prior knowledge (Doctoral dissertation, Université de Lille 1, Sciences et Technologies; CRIStAL UMR 9189).
- ↑ Richard S. Sutton; Andrew G. Barto (2020). Reinforcement Learning: An Introduction (2nd edition). http://incompleteideas.net/book/the-book-2nd.html
 | This psychology-related article is a stub. You can help Wikipedia by expanding it. |
 | This computer science article is a stub. You can help Wikipedia by expanding it. |