Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 56 for “"StarCraft"”.

  1. Proximal Policy Optimization in StarCraft

    … learning. Then we combine them with StarCraft. PPO is the algorithm which have some of the benefits of trust region policy optimization (TRPO), but it is much simpler to implement, more general for environment, and have better sample complexity. The StarCraft environment: Blood War …

    unt Repository record for Proximal Policy Optimization in StarCraft (opens in a new tab)

  2. Regelbaserad AI för StarCraft II

    … använder regelbaserade metoder för att spela StarCraft II, ett datorspel med inkomplett information och många möjliga tillstånd. Spel som detta tillhandahåller tydligt definierade miljöer med stora tillståndsrymder, vilket gör dem till lämpliga plattformar för forskning inom AI. Resultatet av …

    chalmers Repository record for Regelbaserad AI för StarCraft II (opens in a new tab)

  3. Automatický systém pro hraní hry Starcraft

    … automatického systému pro hraní hry Starcraft. Tento systém využívá technik, jako jsou: rozhodovací stromy, konečné automaty a řeší rozhodování v reálném čase, ovládání množství rozdílných jednotek s různými schopnostmi a práci s nekompletní informací o nepříteli. Starcraft: Broodwar …

    brno-tech Repository record for Automatický systém pro hraní hry Starcraft (opens in a new tab)

  4. Posilované učení pro hraní hry Starcraft

    … práce je implementování agenta pro hraní hry Starcraft II. Mnou navržené řešení se učí spolupráci 4 jednoduchých sítí, které se nadále učí optimálně provádět jim přístupné akce ve hře. Analýza a vyhodnocení systému jsou provedeny experimentováním a sbíráním statistik z odehraných her.

    brno-tech Repository record for Posilované učení pro hraní hry Starcraft (opens in a new tab)

  5. Reinforced learning based bot for "starcraft ii" /

    … of an AI bot for the real-time strategy game StarCraft II, leveraging reinforcement learning (RL) techniques to address the complexities of dynamic, large scale environments. Specifically, the project focuses on creating a bot tailored for the Terran race, designed to compete efficiently …

    vilnius Repository record for Reinforced learning based bot for "starcraft ii" / (opens in a new tab)

  6. Řízení boje ve hře Starcraft II pomocí umělé inteligence

    … a návrh funkčného modulu pre strategickú hru StarCraft II. Riešenie využíva neurónové siete a Q-learning pre boj. Pre implementáciu systému a jej prepojenie s hrou StarCraft používam StarCraft 2 Learning Environment. Vyhodnotenie systému je založené na jej schopnosti vykonať pokrok.

    brno-tech Repository record for Řízení boje ve hře Starcraft II pomocí umělé inteligence (opens in a new tab)

  7. Making and Acting on Predictions in StarCraft: Brood War

    … thesis presents how an AI agent, in the game StarCraft, can make use of a Bayesian network to predict the state of the opposing player's technology tree. It is also shown how the predictions can be used to assist the AI agent in making strategic decisions. Bayesian networks are used for the …

    chalmers Repository record for Making and Acting on Predictions in StarCraft: Brood War (opens in a new tab)

  8. Developing game AI for the real-time strategy game StarCraft

    … to hook their AI into the popular RTS game StarCraft. StarCraft provides an interesting platform for AI RTS research due to its large variety of units and balance between playable factions. We designed an AI agent capable of making informed decisions in StarCraft. The agent uses …

    reykjavik Repository record for Developing game AI for the real-time strategy game StarCraft (opens in a new tab)

  9. Developing game AI for the real‐time strategy game StarCraft

    … to hook their AI into the popular RTS game StarCraft. StarCraft provides an interesting platform for AI RTS research due to its large variety of units and balance between playable factions. We designed an AI agent capable of making informed decisions in StarCraft. The agent uses …

    reykjavik Repository record for Developing game AI for the real‐time strategy game StarCraft (opens in a new tab)

  10. Transformer-based Methods for StarCraft Macromanagement And Multi-Agent Reinforcement Learning

    … decision-making in the real-time strategy game, StarCraft II. StarCraft II (SC2) serves as an ideal platform for developing and testing AI agents due to its complexity and strategic depth. SC2 requires players not only to fight skirmishes (micromanagement) but also to build an army and construct …

    ucf Repository record for Transformer-based Methods for StarCraft Macromanagement And Multi-Agent Reinforcement Learning (opens in a new tab)

  11. Zlepšování systému pro automatické hraní hry Starcraft II v prostředí PySC2

    … systému pro hraní strategické hry v reálném čase Starcraft II. Model je trénován ze záznamů her hráčů a dále využívá technik posilovaného učení pro zlepšování vnitřního systému bota. Záměr je vytvořit systém schopný hrát hru jako celek, přičemž staví na frameworku PySC2 pro strojové učení. …

    brno-tech Repository record for Zlepšování systému pro automatické hraní hry Starcraft II v prostředí PySC2 (opens in a new tab)

  12. Machine Learning in StarCraft II - Lowering the Difficulty Threshold of Starting From Scratch

    … industries. In terms of research, games such as StarCraft II provide a good testing ground due to its accessibility. However, getting started can still be more difficult than it should be. This paper aims to facilitate the development of a machine learning agent for StarCraft II by designing …

    chalmers Repository record for Machine Learning in StarCraft II - Lowering the Difficulty Threshold of Starting From Scratch (opens in a new tab)

  13. Jaguar: a hierarchical deep reinforcement learning approach with transfer learning for StarCraft II

    … most relevant information raised were the use of StarCraft II as the main simulation environment, the need for more studies addressing macromanagement, the good performance of hierarchical architectures, and the importance of using action masking and transfer learning techniques, which can reduce …

    brazil-ufrn Repository record for Jaguar: a hierarchical deep reinforcement learning approach with transfer learning for StarCraft II (opens in a new tab)

  14. Developing a Self-learning Intelligent Agent in StarCraft II - Deep Reinforcement Learning with Imitation Learning

    … of machine learning through the complex game StarCraft II with limited prior knowledge and resources. In particular deep Q-learning in combination with imitation learning was explored in order to reduce the time required for an agent to become capable of playing the game. A few simpler …

    chalmers Repository record for Developing a Self-learning Intelligent Agent in StarCraft II - Deep Reinforcement Learning with Imitation Learning (opens in a new tab)

  15. Environmental curriculum learning for efficiently achieving superhuman play in games

    … game Pommerman and real-time strategy game StarCraft II. To allow agents to grasp the many concepts in these games, curriculum learning has been used to teach agents multiple skills over time. We present Environmental Curriculum Learning, a new technique for creating a curriculum of …

    uiuc Repository record for Environmental curriculum learning for efficiently achieving superhuman play in games (opens in a new tab)

  16. Inteligentní systém pro účast v soutěži SSCAI

    … Obsahuje charakteristiku a herní mechaniky hry Starcraft: Brood War, popis pravidel zmíněné soutěže a běžně hrané druhy strategií se zaměřením na civilizaci Zerg a to konkrétně strategie Pool Rush. V soutěži jsem se umístil na sdíleném 10. a 11. místě ze 42zúčastněných. Umělou inteligenci jsem …

    brno-tech Repository record for Inteligentní systém pro účast v soutěži SSCAI (opens in a new tab)

  17. Beyond Star: um modelo de arquitetura de aprendizado para generalização de estratégias em jogos RTS

    … Currently, the field aims to study the RTS using StarCraft I and II as stage of experimentation. The main feature sought in artificial agents developed to this kind of game is high performance, having as its main objective to defeat specialist human players. On this context it is inserted the …

    brazil-ufrn Repository record for Beyond Star: um modelo de arquitetura de aprendizado para generalização de estratégias em jogos RTS (opens in a new tab)

  18. Co-evolving Distributed Control for Heterogeneous Agents in RTS Games

    … called FastEcslent and the popular RTS game, Starcraft II as our test-beds. We represent the problem of generating transparent distributed control in RTS games as a set of numerical parameters that co-evolve to optimize distributed control for agents in multiple skirmish scenarios. This thesis …

    unr Repository record for Co-evolving Distributed Control for Heterogeneous Agents in RTS Games (opens in a new tab)

  19. Modelos e algoritmos para o problema de planejamento para produção de pecursos em jogos de estratégia de tempo real

    … para criação de game AIs competitivas é o StarCraft. Tais game AIs têm dificuldade em se adaptar e criar bons planos para combater a estratégia inimiga. Neste trabalho, um novo modelo de escalonamento de tarefas é proposto modelando os problemas de planejamento em jogos RTS. Este modelo …

    brazil-ufrn Repository record for Modelos e algoritmos para o problema de planejamento para produção de pecursos em jogos de estratégia de tempo real (opens in a new tab)

  20. Řízení entit ve strategické hře založené na multiagentních systémech

    … schopných hry real-time strategických her typu StarCraft. Budou vysvětleny problémy ovládání herních objektů a protivníků počítačem a představeny obvykle používané způsoby řešení. Na základě analýzy je navržen a implementován nový systém využívající multiagentního přístupu k ovládání hry a metod …

    brno-tech Repository record for Řízení entit ve strategické hře založené na multiagentních systémech (opens in a new tab)

Page 1 of 3