Angrier Birds: Bayesian Reinforcement Learning

Abstract

We train a reinforcement learner to play a simplified version of the game Angry Birds. The learner is provided with a game state in a manner similar to the output that could be produced by computer vision algorithms. We improve on the efficiency of regular \{\epsilon\}-greedy Q-Learning with linear function approximation through more systematic exploration in Randomized Least Squares Value Iteration (RLSVI), an algorithm that samples its policy from a posterior distribution on optimal policies. With larger state-action spaces, efficient exploration becomes increasingly important, as evidenced by the faster learning in RLSVI.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyibarra2016angrier

Related papers

• Flapai Bird: Training An Agent To Play Flappy Bird Using Reinforcement Learning Techniques (2020)0.00
• Provably Efficient And Agile Randomized Q-learning (2025)0.00
• Constrained Policy Improvement For Safe And Efficient Reinforcement Learning (2018)0.00
• Bayesian Reparameterization Of Reward-conditioned Reinforcement Learning With Energy-based Models (2023)0.00
• Bayesian Exploration Networks (2023)0.00
• Online Bayesian Risk-averse Reinforcement Learning (2025)0.00
• Safe Imitation Learning Via Fast Bayesian Reward Inference From Preferences (2020)0.00
• An Information-theoretic Optimality Principle For Deep Reinforcement Learning (2017)0.00