Localized Observation Abstraction Using Piecewise Linear Spatial Decay For Reinforcement Learning In Combat Simulations

Abstract

In the domain of combat simulations, the training and deployment of deep reinforcement learning (RL) agents still face substantial challenges due to the dynamic and intricate nature of such environments. Unfortunately, as the complexity of the scenarios and available information increases, the training time required to achieve a certain threshold of performance does not just increase, but often does so exponentially. This relationship underscores the profound impact of complexity in training RL agents. This paper introduces a novel approach that addresses this limitation in training artificial intelligence (AI) agents using RL. Traditional RL methods have been shown to struggle in these high-dimensional, dynamic environments due to real-world computational constraints and the known sample inefficiency challenges of RL. To overcome these limitations, we propose a method of localized observation abstraction using piecewise linear spatial decay. This technique simplifies the state space,

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyblack2024localized

Related papers

• Learning Complex Spatial Behaviours In ABM: An Experimental Observational Study (2022)0.00
• A Survey On Enhancing Reinforcement Learning In Complex Environments: Insights From Human And LLM Feedback (2024)0.00
• Learning Dynamic Abstract Representations For Sample-efficient Reinforcement Learning (2022)0.00
• Scaling Intelligent Agents In Combat Simulations For Wargaming (2024)0.00
• Stabilising Experience Replay For Deep Multi-agent Reinforcement Learning (2017)0.00
• Influence-augmented Local Simulators: A Scalable Solution For Fast Deep RL In Large Networked Systems (2022)0.00
• Efficient Reinforcement Learning Via Decoupling Exploration And Utilization (2023)2.56
• Environment Shaping In Reinforcement Learning Using State Abstraction (2020)0.00