Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Evolutionary Transfer Learning for Dragonchess

Jim O'Connor, Annika Hoag, Sarah Goyette, Gary B. Parker

Abstract

Dragonchess, a three-dimensional chess variant introduced by Gary Gygax, presents unique strategic and computational challenges that make it an ideal environment for studying the transfer of artificial intelligence (AI) heuristics across domains. In this work, we introduce Dragonchess as a novel testbed for AI research and provide an open-source, Python-based game engine for community use. Our research investigates evolutionary transfer learning by adapting heuristic evaluation functions directly from Stockfish, a leading chess engine, and subsequently optimizing them using Covariance Matrix Adaptation Evolution Strategy (CMA-ES). Initial trials showed that direct heuristic transfers were inadequate due to Dragonchess's distinct multi-layer structure and movement rules. However, evolutionary optimization significantly improved AI agent performance, resulting in superior gameplay demonstrated through empirical evaluation in a 50-round Swiss-style tournament. This research establishes the effectiveness of evolutionary methods in adapting heuristic knowledge to structurally complex, previously unexplored game domains.

Evolutionary Transfer Learning for Dragonchess

Abstract

Dragonchess, a three-dimensional chess variant introduced by Gary Gygax, presents unique strategic and computational challenges that make it an ideal environment for studying the transfer of artificial intelligence (AI) heuristics across domains. In this work, we introduce Dragonchess as a novel testbed for AI research and provide an open-source, Python-based game engine for community use. Our research investigates evolutionary transfer learning by adapting heuristic evaluation functions directly from Stockfish, a leading chess engine, and subsequently optimizing them using Covariance Matrix Adaptation Evolution Strategy (CMA-ES). Initial trials showed that direct heuristic transfers were inadequate due to Dragonchess's distinct multi-layer structure and movement rules. However, evolutionary optimization significantly improved AI agent performance, resulting in superior gameplay demonstrated through empirical evaluation in a 50-round Swiss-style tournament. This research establishes the effectiveness of evolutionary methods in adapting heuristic knowledge to structurally complex, previously unexplored game domains.
Paper Structure (23 sections, 2 equations, 2 figures, 1 table)

This paper contains 23 sections, 2 equations, 2 figures, 1 table.

Table of Contents

  1. INTRODUCTION
  2. RELATED WORKS
  3. DRAGONCHESS
  4. METHODOLOGY
  5. Dragonchess Game Engine Development
  6. Transfer of Stockfish Heuristics
  7. Material Values
  8. Piece-Square Tables (PSQT)
  9. Mobility Metrics
  10. King Safety Evaluation
  11. Threat Detection
  12. Passed Pawns (Passed Pieces)
  13. Pawn Count
  14. Imbalance Total
  15. Space Control
  16. ...and 8 more sections

Figures (2)

  • Figure 1: Each board layer (Sky, Ground, and Underground) consists of 8 rows and 12 columns, represented by integer indices from 0 to 287. Each array element at a given index stores an integer constant denoting piece type and ownership (positive integers for Gold, negative integers for Scarlet). This indexing approach enables efficient move generation and heuristic evaluations.
  • Figure 2: Screenshot from our Dragonchess engine's graphical interface built using PyGame. The visualization shows Dragonchess' characteristic three-layered board—Sky (top), Land (middle), and Underworld (bottom)—with distinct piece types and clear depiction of multi-layer interactions and movements unique to Dragonchess.