Reinforcement Learning with Neural Network-based Deterministic Game Tree Approximation
Publication Date
1-1-2023
Document Type
Conference Proceeding
Publication Title
Proceedings - IEEE 9th International Conference on Big Data Computing Service and Applications, BigDataService 2023
DOI
10.1109/BigDataService58306.2023.00039
First Page
181
Last Page
185
Abstract
The goal of reinforcement learning is to learn a policy that maximizes a reward function. In some environments with complete information, search algorithms are highly useful in simulating action sequences in a game tree. However, in many practical environments, such effective search strategies are not applicable since their state transition information may not be available. This paper proposes a novel method to approximate a game tree that enables a reinforcement learning agent to use search strategies even in incomplete information environments. With an approximated game tree, the agent predicts all possible states multiple steps into the future and evaluates the states to determine the best action sequences with the highest return. Our proposal differs from deep reinforcement learning in that it uses deep learning for not only the state evaluation but also game tree approximation. This allows the agent to perform better in completing complex tasks as well as learning tasks in sparse reward environments.
Keywords
planning, reinforcement learning, sparse reward
Department
Computer Science
Recommended Citation
Kevin Prakash and Genya Ishigaki. "Reinforcement Learning with Neural Network-based Deterministic Game Tree Approximation" Proceedings - IEEE 9th International Conference on Big Data Computing Service and Applications, BigDataService 2023 (2023): 181-185. https://doi.org/10.1109/BigDataService58306.2023.00039
