# Two-Step Reinforcement Learning for Multistage Strategy Card Game

arXiv: https://arxiv.org/abs/2311.17305 · HTML: https://mlsanity.com/paper/2311.17305/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 23 references that are in the map.
- First posted on arXiv 29 Nov 2023.

## Builds on (most cited first, 11 of 11)

- [The Hanabi Challenge: A New Frontier for AI Research](https://mlsanity.com/paper/1902.00506/) (2019)
- [Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4](https://mlsanity.com/paper/2309.17277/) (2023)
- [RLCard: A Toolkit for Reinforcement Learning in Card Games](https://mlsanity.com/paper/1910.04376/) (2019)
- [PerfectDou: Dominating DouDizhu with Perfect Information Distillation](https://mlsanity.com/paper/2203.16406/) (2022)
- [Generating and Adapting to Diverse Ad-Hoc Cooperation Agents in Hanabi](https://mlsanity.com/paper/2004.13710/) (2020)
- [Evolutionary Approach to Collectible Card Game Arena Deckbuilding using Active Genes](https://mlsanity.com/paper/2001.01326/) (2020)
- [Evolving Evaluation Functions for Collectible Card Game AI](https://mlsanity.com/paper/2105.01115/) (2021)
- [Learning from Learners: Adapting Reinforcement Learning Agents to be Competitive in a Card Game](https://mlsanity.com/paper/2004.04000/) (2020)
- [Is Vanilla Policy Gradient Overlooked? Analyzing Deep Reinforcement Learning for Hanabi](https://mlsanity.com/paper/2203.11656/) (2022)
- [Optimisation of MCTS Player for The Lord of the Rings: The Card Game](https://mlsanity.com/paper/2109.12001/) (2021)
- [Towards Modern Card Games with Large-Scale Action Spaces Through Action Representation](https://mlsanity.com/paper/2206.12700/) (2022)

## Abstract (arXiv)

In the realm of artificial intelligence and card games, this study introduces a two-step reinforcement learning (RL) strategy tailored for "The Lord of the Rings: The Card Game (LOTRCG)," a complex multistage strategy card game. This research diverges from conventional RL methods by adopting a phased learning approach, beginning with a foundational learning stage in a simplified version of the game and subsequently progressing to the complete, intricate game environment. This methodology notably enhances the AI agent's adaptability and performance in the face of LOTRCG's unpredictable and challenging nature. The paper also explores a multi-agent system, where distinct RL agents are employed for various decision-making aspects of the game. This approach has demonstrated a remarkable improvement in game outcomes, with the RL agents achieving a winrate of 78.5% across a set of 10,000 random games.