Evolutionary Transfer Learning for Dragonchess

• URL: http://arxiv.org/abs/2603.15297v1
• Date: Mon, 16 Mar 2026 13:58:16 GMT
• Title: Evolutionary Transfer Learning for Dragonchess
• Abstract summary: We introduce Dragonchess as a novel testbed for AI research and provide an open-source, Python-based game engine for community use.<n>Our research investigates evolutionary transfer learning by adapting evaluation functions directly from Stockfish, a leading chess engine.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning [51.17262419591891]
  Test-time scaling through iterative self-evolution with environment feedback, as demonstrated by AlphaEvolve, shows remarkable performance gains.<n>We present MetaEvolve, a framework designed to develop these meta-skills via a data synthesis pipeline, evolution-aware reinforcement learning, and inference-time evolutionary search.
  arXiv  Detail & Related papers  (2026-07-24T04:35:29Z)
• Beyond Static Evaluation: Co-Evolutionary Mechanisms for LLM-Driven Strategy Evolution in Adversarial Games [46.73592377177437]
  We show how evaluator co-evolution can replace noisy few-game scores with statistically reliable assessments.<n>We also show how hierarchical deep evaluation replaces noisy few-game scores with statistically reliable assessments.<n>We implement these mechanisms within FAMOU, a framework built upon the same foundation-model code-evolution paradigm as OpenEvolve and ShinkaEvolve.
  arXiv  Detail & Related papers  (2026-06-09T03:55:31Z)
• EvoX: Meta-Evolution for Automated Discovery [115.89434419482797]
  EvoX is an adaptive evolution method that optimize its own evolution process.<n>It continuously updates how prior solutions are selected and varied based on progress.<n>It outperforms existing AI-driven evolutionary methods including AlphaEvolve, OpenEvolve, GEPA, and ShinkaEvolve on the majority of tasks.
  arXiv  Detail & Related papers  (2026-02-26T18:54:41Z)
• Controlled Self-Evolution for Algorithmic Code Optimization [33.82967000330864]
  Self-evolution methods enhance code generation through iterative "generate-verify-refine" cycles.<n>Existing approaches fail to discover solutions with superior complexity within limited budgets.<n>We propose Controlled Self-Evolution (CSE), which consists of three key components.
  arXiv  Detail & Related papers  (2026-01-12T09:23:13Z)
• ThetaEvolve: Test-time Learning on Open Problems [110.5756538358217]
  We introduce ThetaEvolve, an open-source framework that simplifies and extends AlphaEvolve to efficiently scale both in-context learning and Reinforcement Learning (RL) at test time.<n>We find that ThetaEvolve with RL at test-time consistently outperforms inference-only baselines.
  arXiv  Detail & Related papers  (2025-11-28T18:58:14Z)
• Evolution-based Region Adversarial Prompt Learning for Robustness Enhancement in Vision-Language Models [52.8949080772873]
  We propose an evolution-based region adversarial prompt tuning method called ER-APT.<n>In each training iteration, we first generate AEs using traditional gradient-based methods.<n> Subsequently, a genetic evolution mechanism incorporating selection, mutation, and crossover is applied to optimize the AEs.<n>The final evolved AEs are used for prompt tuning, achieving region-based adversarial optimization instead of conventional single-point adversarial prompt tuning.
  arXiv  Detail & Related papers  (2025-03-17T07:08:47Z)
• Learning Evolution via Optimization Knowledge Adaptation [50.280704114978384]
  Evolutionary algorithms (EAs) maintain populations through evolutionary operators to discover solutions for complex tasks.<n>We introduce an Optimization Knowledge Adaptation Evolutionary Model (OKAEM) to enhance its optimization capabilities.<n>OKAEM exploits prior knowledge for significant performance gains across various knowledge transfer settings.<n>It is capable of emulating principles of natural selection and genetic recombination.
  arXiv  Detail & Related papers  (2025-01-04T05:35:21Z)
• Evolution Transformer: In-Context Evolutionary Optimization [6.873777465945062]
  We introduce Evolution Transformer, a causal Transformer architecture, which can flexibly characterize a family of Evolution Strategies. We train the model weights using Evolutionary Algorithm Distillation, a technique for supervised optimization of sequence models. We analyze the resulting properties of the Evolution Transformer and propose a technique to fully self-referentially train the Evolution Transformer.
  arXiv  Detail & Related papers  (2024-03-05T14:04:13Z)
• DARLEI: Deep Accelerated Reinforcement Learning with Evolutionary Intelligence [77.78795329701367]
  We present DARLEI, a framework that combines evolutionary algorithms with parallelized reinforcement learning. We characterize DARLEI's performance under various conditions, revealing factors impacting diversity of evolved morphologies. We hope to extend DARLEI in future work to include interactions between diverse morphologies in richer environments.
  arXiv  Detail & Related papers  (2023-12-08T16:51:10Z)
• Evolutionary Multi-Armed Bandits with Genetic Thompson Sampling [13.173307471333619]
  We propose the Genetic Thompson Sampling, a bandit algorithm that keeps a population of agents and update them with genetic principles such as elite selection, crossover and mutations. We also introduce EvoBandit, a web-based interactive visualization to guide the readers through the entire learning process and perform lightweight evaluations on the fly.
  arXiv  Detail & Related papers  (2022-04-26T22:41:17Z)
• Transfer Dynamics in Emergent Evolutionary Curricula [4.692078300163222]
  PINSKY is a system for open-ended learning through neuroevolution in game-based domains. This paper focuses on the role of transfer of policies from one evolutionary branch ("species") to another. The most insightful finding is that inter-species transfer, while rare, is crucial to the system's success.
  arXiv  Detail & Related papers  (2022-03-03T21:10:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.