Deep reinforcement learning for real world problems
Dota 2 is a popular Multiplayer Online Battle Arena (MOBA) video game. As an Esport, Dota 2 has a prize pool of over USD$40 million in 2021 for its annual flagship competition. Strategy plays a vital role in determining the outcome of games, and teams are constantly looking for means to gain a compe...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project |
| Language: | English |
| Published: |
Nanyang Technological University
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/163306 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Nanyang Technological University |
| Language: | English |
| id |
sg-ntu-dr.10356-163306 |
|---|---|
| record_format |
dspace |
| spelling |
sg-ntu-dr.10356-1633062022-12-01T01:53:49Z Deep reinforcement learning for real world problems Wee, Andrew Chin Ho Bo An School of Computer Science and Engineering boan@ntu.edu.sg Engineering::Computer science and engineering Dota 2 is a popular Multiplayer Online Battle Arena (MOBA) video game. As an Esport, Dota 2 has a prize pool of over USD$40 million in 2021 for its annual flagship competition. Strategy plays a vital role in determining the outcome of games, and teams are constantly looking for means to gain a competitive edge. This work attempts to explore prediction models based solely on the team compositions at the start of a game. In essence, it attempts to predict which team is favoured before actual gameplay begins. Thereafter, we attempt to train and evaluate an AI agent to play the drafting game using Monte Carlo Tree Search. We use data from real matches obtained from the STRATZ API endpoint. Bachelor of Engineering (Computer Science) 2022-12-01T01:53:49Z 2022-12-01T01:53:49Z 2022 Final Year Project (FYP) Wee, A. C. H. (2022). Deep reinforcement learning for real world problems. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/163306 https://hdl.handle.net/10356/163306 en application/pdf Nanyang Technological University |
| institution |
Nanyang Technological University |
| building |
NTU Library |
| continent |
Asia |
| country |
Singapore Singapore |
| content_provider |
NTU Library |
| collection |
DR-NTU |
| language |
English |
| topic |
Engineering::Computer science and engineering |
| spellingShingle |
Engineering::Computer science and engineering Wee, Andrew Chin Ho Deep reinforcement learning for real world problems |
| description |
Dota 2 is a popular Multiplayer Online Battle Arena (MOBA) video game. As an Esport, Dota 2 has a prize pool of over USD$40 million in 2021 for its annual flagship competition. Strategy plays a vital role in determining the outcome of games, and teams are constantly looking for means to gain a competitive edge.
This work attempts to explore prediction models based solely on the team compositions at the start of a game. In essence, it attempts to predict which team is favoured before actual gameplay begins. Thereafter, we attempt to train and evaluate an AI agent to play the drafting game using Monte Carlo Tree Search. We use data from real matches obtained from the STRATZ API endpoint. |
| author2 |
Bo An |
| author_facet |
Bo An Wee, Andrew Chin Ho |
| format |
Final Year Project |
| author |
Wee, Andrew Chin Ho |
| author_sort |
Wee, Andrew Chin Ho |
| title |
Deep reinforcement learning for real world problems |
| title_short |
Deep reinforcement learning for real world problems |
| title_full |
Deep reinforcement learning for real world problems |
| title_fullStr |
Deep reinforcement learning for real world problems |
| title_full_unstemmed |
Deep reinforcement learning for real world problems |
| title_sort |
deep reinforcement learning for real world problems |
| publisher |
Nanyang Technological University |
| publishDate |
2022 |
| url |
https://hdl.handle.net/10356/163306 |
| _version_ |
1751548536454905856 |