Essays about: "agent strategies"

Showing result 21 - 25 of 129 essays containing the words agent strategies.

  1. 21. Exploration-Exploitation Trade-off Approaches in Multi-Armed Bandit

    University essay from Uppsala universitet/Institutionen för informationsteknologi

    Author : Duc Huy Le; [2023]
    Keywords : ;

    Abstract : Multi-armed bandit, a popular framework for sequential decision-making problems, has recently gained significant attention due to numerous applications. In Multi-armed Bandit, an agent faces the central challenge of choosing exploitation of its belief to hopefully gain a high reward and exploration to improve its knowledge of the environment, and any good strategy has to efficiently balance between the two actions. READ MORE

  3. 22. Communication in Multi-agent Games : Defining and Applying Limited Communication in Expanded Multi-agent Games with Imperfect Information Against Nature

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Erik Betzholtz; Maximilian Mannila; [2023]
    Keywords : ;

    Abstract : This thesis studies games where multiple agents attempt to achieve a common objective through various means. The objective will be for the agents to reach a specified state, while reaching a state which makes the objective unattainable will be seen as a loss. READ MORE

  4. 23. Simulation and modelling of crowd control within the context of riots

    University essay from KTH/Datavetenskap

    Author : Erik Hedlund; Tobias Vinsa; [2022]
    Keywords : ;

    Abstract : This project aims to shed light on the abilities of simulation to optimize crowd control management strategies. Simulations were chosen because the difficulties of analyzing crowd control management strategies during an ongoing riot. READ MORE

  5. 24. Self-Play Reinforcement Learning for Finding Intrusion Prevention Strategies

    University essay from KTH/Matematisk statistik

    Author : Jakob Stymne; [2022]
    Keywords : Network security; automation; reinforcement learning; Markov Security Games; Neural Fictitious Self Play; Nätverkssäkerhet; automatisering; förstärkningsinlärning; Markovianska säkerhetsspel; Neural Fictitious Self Play;

    Abstract : This Master thesis studies automated intrusion prevention using self-play reinforcement learning. We extend a decision-theoretic model of the intrusion prevention use case based on optimal stopping theory proposed in previous work to a game-theoretic setting. READ MORE

  6. 25. Investigation on stability of Knowledge Based Subset Construction in Multi-Agent Games

    University essay from KTH/Datavetenskap

    Author : Gustaf Johansson; Gustaf Bergmark; [2022]
    Keywords : Multi-Agent games; Imperfect information; Strategy synthesis; Structural conditions; Fleragentsspel; Ofullständig information; Strategisyntes; Strukturella villkor;

    Abstract : Many real life problems can be modelled using multi-agent games played on finite graphs. When an agent cannot differentiate between game states, for example when a robot operates with a broken sensor, the game is classified as a game of imperfect information. READ MORE