A centralised training algorithm with D3QN for scalable regular unmanned ground vehicle formation maintenance

Computer Science

• training algorithm 100%
• Deep Q-Network 100%
• Deep Reinforcement Learning 66%
• Simulation Experiment 33%
• Learning Framework 33%
• Convergence Speed 33%
• Error Threshold 33%
• Training Environment 33%

Chemical Engineering

• Reinforcement Learning 100%

Engineering

• State of Design 16%