Learning to Play Blackjack: A Curriculum Learning Perspective
This is an incremental improvement for reinforcement learning in games, specifically targeting efficiency and performance in Blackjack.
The paper tackled the problem of reinforcement learning agents struggling with efficiency and performance in complex environments by proposing a framework that uses a Large Language Model to dynamically generate a curriculum over actions, applied to Blackjack, resulting in increased win rates from 43.97% to 47.41%, reduced bust rates from 32.9% to 28.0%, and accelerated training by over 74%.
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.