# Learning to Play Blackjack: A Curriculum Learning Perspective

arXiv: https://arxiv.org/abs/2604.00076 · HTML: https://mlsanity.com/paper/2604.00076/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 35 references that are in the map.
- First posted on arXiv 31 Mar 2026.

## Builds on (most cited first, 14 of 14)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Learning Quadrupedal Locomotion over Challenging Terrain](https://mlsanity.com/paper/2010.11251/) (2020)
- [Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey](https://mlsanity.com/paper/2003.04960/) (2020)
- [Evolving Curricula with Regret-Based Environment Design](https://mlsanity.com/paper/2203.01302/) (2022)
- [Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environments](https://mlsanity.com/paper/1910.07224/) (2019)
- [Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods](https://mlsanity.com/paper/2404.00282/) (2024)
- [Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and Planning](https://mlsanity.com/paper/2210.05492/) (2022)
- [Learning to Generalize from Sparse and Underspecified Rewards](https://mlsanity.com/paper/1902.07198/) (2019)
- [CurricuLLM: Automatic Task Curricula Design for Learning Complex Robot Skills using Large Language Models](https://mlsanity.com/paper/2409.18382/) (2024)
- [A Super-human Vision-based Reinforcement Learning Agent for Autonomous Racing in Gran Turismo](https://mlsanity.com/paper/2406.12563/) (2024)
- [Infinite-Horizon Offline Reinforcement Learning with Linear Function Approximation: Curse of Dimensionality and Algorithm](https://mlsanity.com/paper/2103.09847/) (2021)
- [A Comprehensive Review of Multi-Agent Reinforcement Learning in Video Games](https://mlsanity.com/paper/2509.03682/) (2025)
- [Overcoming the Curse of Dimensionality in Reinforcement Learning Through Approximate Factorization](https://mlsanity.com/paper/2411.07591/) (2024)
- [Assuring the Safety of Reinforcement Learning Components: AMLAS-RL](https://mlsanity.com/paper/2507.08848/) (2025)

## Abstract (arXiv)

Reinforcement Learning (RL) agents often struggle with efficiency and performance in complex environments. We propose a novel framework that uses a Large Language Model (LLM) to dynamically generate a curriculum over available actions, enabling the agent to incorporate each action individually. We apply this framework to the game of Blackjack, where the LLM creates a multi-stage training path that progressively introduces complex actions to a Tabular Q-Learning and a Deep Q-Network (DQN) agent. Our evaluation in a realistic 8-deck simulation over 10 independent runs demonstrates significant performance gains over standard training methods. The curriculum-based approach increases the DQN agent's average win rate from 43.97% to 47.41%, reduces the average bust rate from 32.9% to 28.0%, and accelerates the overall workflow by over 74%, with the agent's full training completing faster than the baseline's evaluation phase alone. These results validate that LLM-guided curricula can build more effective, robust, and efficient RL agents.