Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Introducing Tales of Tribute AI Competition

Jakub Kowalski, Radosław Miernik, Katarzyna Polak, Dominik Budzki, Damian Kowalik

TL;DR

This work addresses AI for a complex deck-building CCG with randomness and partial information by introducing the Tales of Tribute AI Competition (TOTAIC) and its supporting framework. It demonstrates that a broad suite of AI techniques—including adversarial search (MCTS, Minimax), planning (Rolling Horizon Evolution, Beam Search), and neural-network-inspired methods—can tackle the unique challenges of deck-building, patron mechanics, and tavern dynamics. The paper reports a tournament among diverse sample agents, identifies top-performing approaches (notably MCTS, Decision Tree, and Beam Search), and presents a winner based on root-parallelized MCTS with seed-aware evaluation and tier-based card scoring. The work contributes a practical benchmark, an extensible engine, and experimental evidence that a hybrid, multi-technique strategy offers robust performance in ToT, providing a platform to advance AI research in deck-building and CCG domains with real-world relevance to ESO players.

Abstract

This paper presents a new AI challenge, the Tales of Tribute AI Competition (TOTAIC), based on a two-player deck-building card game released with the High Isle chapter of The Elder Scrolls Online. Currently, there is no other AI competition covering Collectible Card Games (CCG) genre, and there has never been one that targets a deck-building game. Thus, apart from usual CCG-related obstacles to overcome, like randomness, hidden information, and large branching factor, the successful approach additionally requires long-term planning and versatility. The game can be tackled with multiple approaches, including classic adversarial search, single-player planning, and Neural Networks-based algorithms. This paper introduces the competition framework, describes the rules of the game, and presents the results of a tournament between sample AI agents.

Introducing Tales of Tribute AI Competition

TL;DR

This work addresses AI for a complex deck-building CCG with randomness and partial information by introducing the Tales of Tribute AI Competition (TOTAIC) and its supporting framework. It demonstrates that a broad suite of AI techniques—including adversarial search (MCTS, Minimax), planning (Rolling Horizon Evolution, Beam Search), and neural-network-inspired methods—can tackle the unique challenges of deck-building, patron mechanics, and tavern dynamics. The paper reports a tournament among diverse sample agents, identifies top-performing approaches (notably MCTS, Decision Tree, and Beam Search), and presents a winner based on root-parallelized MCTS with seed-aware evaluation and tier-based card scoring. The work contributes a practical benchmark, an extensible engine, and experimental evidence that a hybrid, multi-technique strategy offers robust performance in ToT, providing a platform to advance AI research in deck-building and CCG domains with real-world relevance to ESO players.

Abstract

This paper presents a new AI challenge, the Tales of Tribute AI Competition (TOTAIC), based on a two-player deck-building card game released with the High Isle chapter of The Elder Scrolls Online. Currently, there is no other AI competition covering Collectible Card Games (CCG) genre, and there has never been one that targets a deck-building game. Thus, apart from usual CCG-related obstacles to overcome, like randomness, hidden information, and large branching factor, the successful approach additionally requires long-term planning and versatility. The game can be tackled with multiple approaches, including classic adversarial search, single-player planning, and Neural Networks-based algorithms. This paper introduces the competition framework, describes the rules of the game, and presents the results of a tournament between sample AI agents.
Paper Structure (35 sections, 4 figures, 3 tables)

This paper contains 35 sections, 4 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related AI Competitions
  3. Hearthstone AI Competition
  4. Strategy Card Game AI Competition
  5. Related Research
  6. Tales of Tribute Card Game
  7. Game Rules
  8. Starting a match
  9. General playing rules
  10. Cards
  11. Combo Effects
  12. Keywords
  13. Patrons
  14. Winning
  15. Playing strategy
  16. ...and 20 more sections

Figures (4)

  • Figure 1: Tales of Tribute in The Elder Scrolls Online.
  • Figure 2: Graphical user interface of the game within Scripts of Tribute framework.
  • Figure 3: Results of the tournament between all sample agents.
  • Figure 4: Beam Search versus MCTS depending on the beam width and player order. As we can see, winning as the second player is significantly harder.