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 39 for “"Self - play"”.

  1. Mastering Cooperative, Incomplete Information Board Games by Self-Play

    … racing games with imperfect information and team play. These game characteristics bring more complexity after the successes of RL research on perfect information games like Go and Chess.<br/>This research is based on, and part of, broader developments in RL. The study of re-lated work led to the …

    openu Repository record for Mastering Cooperative, Incomplete Information Board Games by Self-Play (opens in a new tab) Download PDF for Mastering Cooperative, Incomplete Information Board Games by Self-Play (opens in a new tab)

  2. From brittle to robust : adversarial self-play for robust reasoning

    … We introduce GASP (Guided Adversarial Self-Play), a robustification method that explicitly trains detect-and-repair capabilities using only outcome verification. Without human labels or external teachers, GASP forms an adversarial self-play game within a single model: a polluter learns …

    texas Repository record for From brittle to robust : adversarial self-play for robust reasoning (opens in a new tab)

  3. Approximate universal artificial intelligence and self-play learning for games

    … The second part of this thesis looks at self-play learning in two player, deterministic, adversarial turn-based games. The main contribution is the introduction of a new technique for training the weights of a heuristic evaluation function from data collected by classical game tree search …

    unsw Repository record for Approximate universal artificial intelligence and self-play learning for games (opens in a new tab)

  4. Expediting self-play learning in AlphaZero-style game-playing agents

    One of the main appeals of AlphaZero-style game-playing agents, which combine deep learning and Monte Carlo Tree Search, is that they can be trained autonomously without external expert-level domain knowledge. However, training such agents is generally computationally expensive, with the most …

    reykjavik Repository record for Expediting self-play learning in AlphaZero-style game-playing agents (opens in a new tab)

  5. Comparison of deep reinforcement learning algorithms in a self-play setting

    … in deep reinforcement learning, especially under self-play settings. The methods used by AlphaZero are finding their ways to be more useful than before in many different application areas, such as clinical medicine, intelligent military command decision support systems, and recommendation systems. …

    uvic Repository record for Comparison of deep reinforcement learning algorithms in a self-play setting (opens in a new tab)

  6. Hierarchical policy design for sample-efficient learning of robot table tennis through self-play

    … and analytic controllers for the robot itself. Human demonstrations are used to train dynamics models, which together with the analytic controller allow any robot that is physically capable to play table tennis without training episodes. Using only about 7000 demonstrated trajectories, a …

    texas Repository record for Hierarchical policy design for sample-efficient learning of robot table tennis through self-play (opens in a new tab)

  7. A Self-Trained Engine for a Chess Variant

    … Recent advances, such as AlphaZero, introduced self-learning AI through reinforcement learning and self-play, achieving superhuman performance without prior strategic knowledge, relying solely on the rules of the game. AlphaZero defeated the world-champion chess engine Stockfish after only four …

    chalmers Repository record for A Self-Trained Engine for a Chess Variant (opens in a new tab)

  8. Limitations and Extensions of the WoLF-PHC Algorithm

    … principle. A proof that PHC will diverge in self-play when playing Shapley's game is given, and WoLF-PHC is shown empirically to diverge as well. Various WoLF-PHC based modifications were created, evaluated, and compared in an attempt to obtain convergence to the single shot Nash equilibrium …

    byu Repository record for Limitations and Extensions of the WoLF-PHC Algorithm (opens in a new tab) Download PDF for Limitations and Extensions of the WoLF-PHC Algorithm (opens in a new tab)

  9. Sample Efficient Game Strategy Through Active Demonstrations

    AlphaZero-style learning trains agents in game-playing purely through self-play, but requires millions of games before converging. In domains like robotics, imitation learning has been used to increase sample efficiency. The goal of this thesis is to incorporate imitation learning and expert …

    chalmers Repository record for Sample Efficient Game Strategy Through Active Demonstrations (opens in a new tab)

  10. Aprendendo estratégias programáticas através de características comporta- mentais

    … modo, utiliza-se atualmente uma abordagem de self-play para guiar a busca. No entanto, essa abordagem geralmente fornece um fraco sinal para guiar a busca, uma vez que o self-play só é ca- paz de avaliar o desempenho de um programa em relação a outros programas. Assim, enquanto pequenas …

    brazil-ufv Repository record for Aprendendo estratégias programáticas através de características comporta- mentais (opens in a new tab)

  11. Neural network guided monte carlo tree search for liar's dice /

    … (MCTS) for Liar's Dice. The game is a four-player imperfect-information game where players make bids while observing only their own dice and reasoning about their opponents' hidden dice. The aim of the thesis was to implement and evaluate a neural-guided Information Set Monte Carlo Tree …

    vilnius Repository record for Neural network guided monte carlo tree search for liar's dice / (opens in a new tab)

  12. Multimodal probabilistic reasoning for prediction and coordination problems in machine learning

    … in this area has been confined to considering a self-play paradigm, even if the approaches tackle a variety of challenging problems. Whilst these advances are significant, the use of arbitrary conventions in self-play leads to coordination problems when agents play outside this setting. We …

    oxford Repository record for Multimodal probabilistic reasoning for prediction and coordination problems in machine learning (opens in a new tab)

  13. A Self-Trained Chess Engine for Crazyhouse Chess

    This thesis investigates the development of a self-trained chess engine for the Crazy house chess variant, inspired by the AlphaZero framework. Crazyhouse extends classical chess with a drop mechanic, where captured pieces can be collected and reintroduced onto the board, fundamentally altering …

    chalmers Repository record for A Self-Trained Chess Engine for Crazyhouse Chess (opens in a new tab)

  14. From MDP to AlphaZero

    … Carlo Tree Search (MCTS) with Deep learning and self-play. We will see how these three concepts fit together and we will break down each of these pieces and look at examples to clarify understanding. I implemented a simplified version of the algorithm on TicTacToe and Connect4 and the code is …

    portland-state Repository record for From MDP to AlphaZero (opens in a new tab)

  15. Single-player to Two-player Knowledge Transfer in Atari 2600 Games

    Playing two-player games using reinforcement learning and self-play can be challenging due to the complexity of two-player environments and the potential instability in the training process. It is proposed that a reinforcement learning algorithm can train more efficiently and achieve improved …

    calgary Repository record for Single-player to Two-player Knowledge Transfer in Atari 2600 Games (opens in a new tab)

  16. A Self–Trained Engine for Atomic Chess

    … concerns the development of a chess engine to play a variant of chess called atomic chess, utilizing a neural network. The neural network is modeled after DeepMind’s AlphaZero, which is a model that learned standard chess from only the rules, and no real-world games (hence “zero”). We …

    chalmers Repository record for A Self–Trained Engine for Atomic Chess (opens in a new tab)

  17. Improving Convergence Rates in Multiagent Learning Through Experts and Adaptive Consultation

    … converges to the set of Nash equilibria in self-play, while consulting experts which can greatly improve the convergence rate to the set of equilibria. Even if the experts are not well suited to the learning problem, or are hostile, then FRAME will still provably converge. Our second …

    waterloo Repository record for Improving Convergence Rates in Multiagent Learning Through Experts and Adaptive Consultation (opens in a new tab)

  18. Experimenting with time and depth control in chess engines

    … Shogi, and Go through machine-learning and self-play using no game-specific knowledge features (except the rules of the games). In this project, we examine ways to improve chess playing programs using machine learning methods. In our first set of experiments, we test whether a neural network …

    reykjavik Repository record for Experimenting with time and depth control in chess engines (opens in a new tab)

  19. Multi-agent Coordination Algorithms for Pursuit-Evasion

    … of large-scale multi-agent systems, as some self-organizing systems in nature. Particularly, five research questions are answered in the thesis: (1) how to resolve collisions in the multi-agent environment; (2) how to be cooperative in a distributed way; (3) how to allocate the multi-agent …

    uts Repository record for Multi-agent Coordination Algorithms for Pursuit-Evasion (opens in a new tab)

  20. VGC-bench : towards mastering diverse team strategies in competitive Pokémon

    … evaluation protocols, and supplies human-play datasets and a range of baselines -- from large-language-model agents and behavior cloning to reinforcement learning and empirical game-theoretic methods such as self-play, fictitious play, and double oracle. In the restricted setting where an …

    texas Repository record for VGC-bench : towards mastering diverse team strategies in competitive Pokémon (opens in a new tab)

Page 1 of 2