logo
avatarLog in
中文
Gaming Algorithm - Intermediate Track
Competition Status已结束
Total Prize¥ 200000

Track Introductionspecial-title-icon

This track is a medium difficulty level segment of the Tencent AI Arena Artificial Intelligence National Open Competition, primarily designed for university students who are newcomers to the field of reinforcement learning and have an interest in it. The schedule for this track mainly includes pre-competition training courses in reinforcement learning, as well as three stages: open qualifiers, semi-finals, and finals.

Target Participants

This track is open for registration to full-time junior college and undergraduate students who are currently enrolled. Each team must consist of members from the same university, with a maximum of five members and at least one faculty advisor. There are no restrictions on the members' majors, and each individual can only join one team. Graduate students and those with higher academic qualifications are encouraged to participate in the 'Gaming Algorithm - Advanced Track'.

Rewardsspecial-title-icon

Teams that successfully submit models and participate in the rankings for the open qualifiers, semi-finals, and finals can receive the following prize. The amounts are in RMB (pre-tax).

Champion: Prize money 60,000 RMB + Competition Certificate + Trophy

Runner-up: Prize money RMB 30,000 + Competition Certificate + Trophy

Third Place: Prize money RMB 20,000 + Competition Certificate + Trophy

Excellence Award (4-8th place): Prize Money RMB 10,000 + Competition Certificate

Merit Award (9-16th place): Prize money RMB 5,000 + Competition Certificate

Additional Rewards

In addition to the prize money, participating teams can also receive the following rewards:

1.Official participation certificates for completing the open qualifiers (successful model submission and validation).

2.Outstanding participants may have the opportunity to obtain internships related to the Tencent AI Arena project, as well as eligibility for Tencent Group's campus recruitment and internship recruitment fast track. Specific details will be announced separately.

3.Outstanding teams will be invited to participate in sharing sessions at the Tencent STAC.

Open Qualifiers
Time period: July 31st to August 11th
This round evaluates the fundamental game AI development skills.
Gorge Walk
Scenario Type: PVE (Player vs. Environment)
Map: Gorge Forest
Lineup: Luban No.7
Number of agents: 1
Evaluation Method: Train models locally using the Tencent AI Arena client and submit them to the Tencent AI Arena platform for uniform execution.
Computational Resources: This track uses the participants' local computational resources.

Description: Gorge Walk utilizes the Gorge Forest map, featuring a starting point, an ending point, a road, obstacles, acceleration gains, and treasure chests. The agent does not have a full view of the map and can move within it, use summoner skills, and collect rewards from treasure chests. The agent cannot continue forward upon encountering obstacles. The agent must reach the endpoint within a set time, or it will be deemed as a mission timeout. (After successful registration, a detailed development guide is available on the platform.)

Task Objective: To drive the agent through algorithmically trained models, enabling it to learn movement strategies through continuous exploration of test maps. The objective is to efficiently use summoner skills and speed boosts to collect treasure chests, avoid obstacles, and reach the endpoint within a limited time. Participating teams must train and submit a model locally within the designated time, and control the hero Luban No. 7 in the assessment map to score as many points as possible in the least amount of time, thereby completing the Gorge Walk's map exploration target.

Ranking Rules: In the last week of the competition, the system will automatically run with the latest model submitted by the participating teams. Their total score will be the team's ranking score, which will be the final result of the open qualifiers. The top 80 teams completing the challenge in this track will advance to the semi-finals.

Semi-finals
Time period: August to October (6 weeks of competition)
This round emphasizes single-agent solutions, model structure design, reinforcement learning algorithm design, and training method exploration.
Honor of Kings 1v1
Scenario Type: PVP (competing against other participants)
Map: Mojia Map
Lineup: To be announced (single lineup)
Number of agents: 1
Evaluation Method: Submit the model to Tencent AI Arena Platform for uniform execution by the platform.
Computational Resources: During this stage of the competition, each advancing team will receive an equal amount of computational resources provided by the platform.

Description: This stage of the competition uses the Honor of Kings' 1v1 Mojia Map, which is elongated in shape. At both ends of the map are the revival points for the two agents, with the team's crystal located in front of the revival point. The crystal continuously produces minions for its team, which will automatically move towards the enemy's camp, attacking enemy towers, crystals, and heroes along the way. In front of the crystal is the team's defense towers, which can attack enemy heroes and minions entering its range. Agents can freely move and use skills within the map. Over time, agents gain gold and experience, with significant amounts earned from killing enemy minions, enemy heroes, or destroying enemy towers. The team that successfully destroys the opponent's crystal wins the round.

Task Objective: Train models within a designated time and given computational resources to learn the optimal winning strategy through continuous exploration of the 1v1 map.

Scoring Rules: In each round of competition between two teams, both heroes must play two matches, switching sides to battle against the opposing hero. Winning a match earns one point, while losing scores no points.

Ranking Rules: In the last week of the competition, the system will automatically conduct battles using the latest models submitted by the participating teams. The number of rounds for each leaderboard battle is to be determined. Teams will be ranked based on their accumulated points. This ranking will be the final result of the semi-finals, with the top 8 teams advancing to the finals.

Finals
Time period: October to November (6 weeks of competition)
Compared to the semi-finals, the finals involve multi-agent solutions (emphasizing cooperation among AIs) and the gaming environment used in the competition has a larger state space, requiring more complex model structures and advanced reinforcement learning algorithms. Additionally, participants need to consider the design of reward functions, explore training methods, and other aspects.
Honor of Kings 5v5 Dreamland Clash
Scenario Type: PVP (competing against other participants)
Map: Dreamland Clash
Lineup: To be announced (single lineup)
Number of agents: 5
Evaluation Method: Submit models to Tencent AI Arena for uniform execution by the platform.
Computational Resources: During this stage of the competition, each advancing team will receive an equal amount of computational resources provided by the platform.

Description: This match utilizes the Honor of Kings 5v5 Dreamland Clash map, which is elongated in shape. At each end of the map are the revival points for each team's agents, with the team's crystal located in front of the revival point. The crystal continuously produces minions for its team, which automatically advance towards the enemy's camp, attacking enemy towers, crystals, and heroes along the way. In front of the crystal is the team's defense towers, capable of attacking enemy heroes and minions entering its range. Agents can freely move and use skills within the map. Over time, agents gain gold and experience, with significant rewards for killing enemy minions, enemy heroes, or destroying enemy towers. The team that successfully destroys the opponent's crystal wins the match.

Task Objective: Train models within a designated time and given computational resources to learn the optimal winning strategy through continuous exploration of the 5v5 map.

Scoring Rules: In each round of competition between two teams, the lineups will switch sides for two matches, with each victory earning one point and losses scoring no points.

Ranking Rules: The number of rounds for each leaderboard battle is to be determined, and teams will be ranked based on their points.

Requirementsspecial-title-icon

It is recommended that each team possesses at least one computer that meets the following recommended specifications, to set up the local environment, carry out local development, and submit tasks to the cluster.

Operation system:

Windows10

CPU:

i5-9th Generation

Memory:

16GB

FAQspecial-title-icon

Q: For other registration inquiries, how can I reach out to the organizing committee?
A: Feel free to join the official QQ group of the organizing committee: 732115106 to connect with us.
For any further registration inquiries, please join the Q&A QQ group with the number 732115106