Reinforcement Learning For Constraint Satisfaction Game Agents (15-puzzle, Minesweeper, 2048, And Sudoku)

Abstract

In recent years, reinforcement learning has seen interest because of deep Q-Learning, where the model is a convolutional neural network. Deep Q-Learning has shown promising results in games such as Atari and AlphaGo. Instead of learning the entire Q-table, it learns an estimate of the Q function that determines a state's policy action. We use Q-Learning and deep Q-learning, to learn control policies of four constraint satisfaction games (15-Puzzle, Minesweeper, 2048, and Sudoku). 15-Puzzle is a sliding permutation puzzle and provides a challenge in addressing its large state space. Minesweeper and Sudoku involve partially observable states and guessing. 2048 is also a sliding puzzle but allows for easier state representation (compared to 15-Puzzle) and uses interesting reward shaping to solve the game. These games offer unique insights into the potential and limits of reinforcement learning. The Q agent is trained with no rules of the game, with only the reward corresponding to each st

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keymehta2021reinforcement

Related papers

• Monte Carlo Q-learning For General Game Playing (2018)0.00
• Reinforcement Learning And Video Games (2019)0.00
• Simplified Action Decoder For Deep Multi-agent Reinforcement Learning (2019)4.03
• Transformer Based Reinforcement Learning For Games (2019)0.00
• Reinforcing Competitive Multi-agents For Playing 'so Long Sucker' (2024)0.00
• Multi-task Curriculum Learning In A Complex, Visual, Hard-exploration Domain: Minecraft (2021)0.00
• Performing Deep Recurrent Double Q-learning For Atari Games (2019)10.07
• From Two-dimensional To Three-dimensional Environment With Q-learning: Modeling Autonomous Navigation With Reinforcement Learning And No Libraries (2024)0.00