Material Type  

 학위논문

 

0016935532

Date and Time of Latest Transaction  

20240214101944

ISBN  

9798380370998

DDC  

004

Author  

Smith, Max Olan.

Title/Author  

Efficient Game Solving Through Transfer Learning - [electronic resource]

Publish Info  

[S.l.] : University of Michigan., 2023

Publish Info  

Ann Arbor : ProQuest Dissertations & Theses, 2023

Material Info  

1 online resource(161 p.)

General Note  

Source: Dissertations Abstracts International, Volume: 85-03, Section: B.

General Note  

Advisor: Wellman, Michael P.

학위논문주기  

Thesis (Ph.D.)--University of Michigan, 2023.

Restrictions on Access Note  

This item must not be sold to any third party vendors.

Restrictions on Access Note  

This item must not be added to any third party search indexes.

Abstracts/Etc  

요약Game-solving approaches using reinforcement learning often entail a significant computational cost. This arises from the necessity of training agents to play with or against a series of other-agent strategies. Each round of training brings us closer to the game's solution, but training an agent can require data from millions of games played-typically in simulation. The cost of game solving reflects the cumulative data cost of repeatedly training agents. This cost is also a result of treating each training as an independent problem. However, these problems share elements that reflect the nature of the game-solving process. These similarities present an opportunity for an agent to transfer learning from previous problems to aid in solving the current problem.In this dissertation, I develop a collection of new game-solving algorithms that are based on new methods for transfer learning, thereby reducing the computational cost of game solving. I explore two types of transferable knowledge: strategic and world. Strategic knowledge describes knowledge that depends on the other agents. In the simplest case, strategic knowledge may be encapsulated in a policy that was trained to play, with or against, fixed other agents. To facilitate the transfer of this kind of strategic knowledge, I propose Q-Mixing, a technique that constructs a policy to play against a distribution of other agents by combining strategic knowledge regarding each agent in the distribution. I provide a practical approximate version of Q-Mixing that features another type of strategic knowledge: a learned belief in the distribution of the other agents. I then develop two game-solving algorithms, Mixed-Oracles and Mixed-Opponents. These algorithms use Q-Mixing to shift the learning focus from interacting with a distribution of other agents to concentrating on a single other agent. This transition results in a significantly easier and, therefore, less costly learning problem. Complementary to strategic knowledge, world knowledge is independent of the other agents. I demonstrate that co-learning a world model along with game solving allows the world model to benefit from more strategically diverse training data. It also renders game solving more affordable through planning. I realize both of these benefits in a new game-solving algorithm Dyna-PSRO. Overall, this dissertation introduces new techniques and demonstrates their effectiveness in significantly reducing the cost of game solving. By doing so, it further enables learning-based game-solving algorithms to be applied to more complex games.

Subject Added Entry-Topical Term  

Computer science.

Subject Added Entry-Topical Term  

Computer engineering.

Index Term-Uncontrolled  

Reinforcement learning

Index Term-Uncontrolled  

Multiagent learning

Index Term-Uncontrolled  

Computational cost

Index Term-Uncontrolled  

Game-solving algorithms

Index Term-Uncontrolled  

Transfer learning

Added Entry-Corporate Name  

University of Michigan Computer Science & Engineering

Host Item Entry  

Dissertations Abstracts International. 85-03B.

Host Item Entry  

Dissertation Abstract International

Electronic Location and Access  

로그인을 한후 보실 수 있는 자료입니다.

소장사항  

202402 2024

Control Number  

joongbu:641203