Loading...
Please wait, while we are loading the content...
Similar Documents
The UCT algorithm applied to find the best first move in the game of Tic-Tac-Toe
| Content Provider | Semantic Scholar |
|---|---|
| Author | Lee, Byung-Doo Park, Dong-Soo Choi, Young-Wook |
| Copyright Year | 2015 |
| Abstract | The game of Go originated from ancient China is regarded as one of the most difficult challenges in the filed of AI. Over the past few years, the top computer Go programs based on MCTS have surprisingly beaten professional players with handicap. MCTS is an approach that simulates a random sequence of legal moves until the game is ended, and replaced the traditional knowledge-based approach. We applied the UCT algorithm which is a MCTS variant to the game of Tic-Tac-Toe for finding the best first move, and compared it with the result generated by a pure MCTS. Furthermore, we introduced and compared the performances of epsilon-Greedy algorithm and UCB algorithm for solving the Multi-Armed Bandit problem to understand the UCB. |
| Starting Page | 109 |
| Ending Page | 118 |
| Page Count | 10 |
| File Format | PDF HTM / HTML |
| DOI | 10.7583/JKGS.2015.15.5.109 |
| Volume Number | 15 |
| Alternate Webpage(s) | http://ocean.kisti.re.kr/downfile/volume/kgames/KGOHCL/2015/v15n5/KGOHCL_2015_v15n5_109.pdf |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
