5 citations · 11 across the 18 of their papers we have counts for
18 papers
MAPLE: Multi-State Aggregated Policy Evaluation for AlphaZero in Imperfect-Information Games
Qian-Rong Li, Hung Guei, I-Chen Wu +1
Imperfect-information games (IIGs) are challenging, as players must make decisions without fully observing the true game state. While AlphaZero has achieved remarkable success in p…
A Study of Solving Life-and-Death Problems in Go Using Relevance-Zone Based Solvers
Chung-Chin Shih, Ti-Rong Wu, Ting Han Wei +3
This paper analyzes the behavior of solving Life-and-Death (L&D) problems in the game of Go using current state-of-the-art computer Go solvers with two techniques: the Relevance-Zo…
Learning Human-Like RL Agents Through Trajectory Optimization With Action Quantization
Jian-Ting Guo, Yu-Cheng Chen, Ping-Chun Hsieh +4
Human-like agents have long been one of the goals in pursuing artificial intelligence. Although reinforcement learning (RL) has achieved superhuman performance in many domains, rel…
Relevance-Zone Reduction in Game Solving
Chi-Huang Lin, Ting Han Wei, Chun-Jui Wang +5
Game solving aims to find the optimal strategies for all players and determine the theoretical outcome of a game. However, due to the exponential growth of game trees, many games r…
Dynamic Sight Range Selection in Multi-Agent Reinforcement Learning
Wei-Chen Liao, Ti-Rong Wu, I-Chen Wu
Multi-agent reinforcement Learning (MARL) is often challenged by the sight range dilemma, where agents either receive insufficient or excessive information from their environment.…
Strength Estimation and Human-Like Strength Adjustment in Games
Chun Jung Chen, Chung-Chin Shih, Ti-Rong Wu
Strength estimation and adjustment are crucial in designing human-AI interactions, particularly in games where AI surpasses human players. This paper introduces a novel strength sy…
OptionZero: Planning with Learned Options
Po-Wei Huang, Pei-Chiun Peng, Hung Guei +1
Planning with options -- a sequence of primitive actions -- has been shown effective in reinforcement learning within complex environments. Previous studies have focused on plannin…
Solving 7x7 Killall-Go with Seki Database
Yun-Jui Tsai, Ting Han Wei, Chi-Huang Lin +4
Game solving is the process of finding the theoretical outcome for a game, assuming that all player choices are optimal. This paper focuses on a technique that can reduce the heuri…
Demystifying MuZero Planning: Interpreting the Learned Model
Hung Guei, Yan-Ru Ju, Wei-Yu Chen +1
MuZero has achieved superhuman performance in various games by using a dynamics network to predict the environment dynamics for planning, without relying on simulators. However, th…
Bridging Local and Global Knowledge via Transformer in Board Games
Yan-Ru Ju, Tai-Lin Wu, Chung-Chin Shih +1
Although AlphaZero has achieved superhuman performance in board games, recent studies reveal its limitations in handling scenarios requiring a comprehensive understanding of the en…
Game Solving with Online Fine-Tuning
Ti-Rong Wu, Hung Guei, Ting Han Wei +3
Game solving is a similar, yet more difficult task than mastering a game. Solving a game typically means to find the game-theoretic value (outcome given optimal play), and optional…
MiniZero: Comparative Analysis of AlphaZero and MuZero on Go, Othello, and Atari Games
Ti-Rong Wu, Hung Guei, Pei-Chiun Peng +4
This paper presents MiniZero, a zero-knowledge learning framework that supports four state-of-the-art algorithms, including AlphaZero, MuZero, Gumbel AlphaZero, and Gumbel MuZero.…
A Local-Pattern Related Look-Up Table
Chung-Chin Shih, Ting Han Wei, Ti-Rong Wu +1
This paper describes a Relevance-Zone pattern table (RZT) that can be used to replace a traditional transposition table. An RZT stores exact game values for patterns that are disco…
Are AlphaZero-like Agents Robust to Adversarial Perturbations?
Li-Cheng Lan, Huan Zhang, Ti-Rong Wu +3
The success of AlphaZero (AZ) has demonstrated that neural-network-based Go AIs can surpass human performance by a large margin. Given that the state space of Go is extremely large…
A Novel Approach to Solving Goal-Achieving Problems for Board Games
Chung-Chin Shih, Ti-Rong Wu, Ting Han Wei +1
Goal-achieving problems are puzzles that set up a specific situation with a clear objective. An example that is well-studied is the category of life-and-death (L&D) problems for Go…
Learning to Stop: Dynamic Simulation Monte-Carlo Tree Search
Li-Cheng Lan, Meng-Yu Tsai, Ti-Rong Wu +2
Monte Carlo tree search (MCTS) has achieved state-of-the-art results in many domains such as Go and Atari games when combining with deep neural networks (DNNs). When more simulatio…
Accelerating and Improving AlphaZero Using Population Based Training
Ti-Rong Wu, Ting-Han Wei, I-Chen Wu
AlphaZero has been very successful in many games. Unfortunately, it still consumes a huge amount of computing resources, the majority of which is spent in self-play. Hyperparameter…
Multi-Labelled Value Networks for Computer Go
Ti-Rong Wu, I-Chen Wu, Guan-Wun Chen +4
This paper proposes a new approach to a novel value network architecture for the game Go, called a multi-labelled (ML) value network. In the ML value network, different values (win…