Reinforcement Learning Agent For A 2D Shooter Game

Abstract

Reinforcement learning agents in complex game environments often suffer from sparse rewards, training instability, and poor sample efficiency. This paper presents a hybrid training approach that combines offline imitation learning with online reinforcement learning for a 2D shooter game agent. We implement a multi-head neural network with separate outputs for behavioral cloning and Q-learning, unified by shared feature extraction layers with attention mechanisms. Initial experiments using pure deep Q-Networks exhibited significant instability, with agents frequently reverting to poor policies despite occasional good performance. To address this, we developed a hybrid methodology that begins with behavioral cloning on demonstration data from rule-based agents, then transitions to reinforcement learning. Our hybrid approach achieves consistently above 70% win rate against rule-based opponents, substantially outperforming pure reinforcement learning methods which showed high variance and

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyackermann2025reinforcement

Related papers

• Learning To Shoot In First Person Shooter Games By Stabilizing Actions And Clustering Rewards For Reinforcement Learning (2018)0.00
• Adaptive Shooting For Bots In First Person Shooter Games Using Reinforcement Learning (2018)0.00
• Deep Reinforcement Learning For Doom Using Unsupervised Auxiliary Tasks (2018)0.00
• Mimicking To Dominate: Imitation Learning Strategies For Success In Multiagent Competitive Games (2023)0.00
• Reinforcing Competitive Multi-agents For Playing 'so Long Sucker' (2024)0.00
• A Human Mixed Strategy Approach To Deep Reinforcement Learning (2018)7.50
• Applying Supervised And Reinforcement Learning Methods To Create Neural-network-based Agents For Playing Starcraft II (2021)0.00
• Discriminator Soft Actor Critic Without Extrinsic Rewards (2020)3.58