Managing engineering systems with large state and action spaces through deep reinforcement learning

Engineering

• Reinforcement Learning 100%
• Systems Engineering 100%
• Partially Observable Markov Decision Process 100%
• Action Space 100%
• Multicomponent System 66%
• Dimensional Space 33%
• Value Function 33%
• Lifecycle 33%
• Solution Procedure 33%
• Decision Level 33%
• System State 33%
• Approximators 33%
• Markov Decision Process 33%

Computer Science

• And-States 100%
• Markov Decision Process 100%
• Deep Reinforcement Learning 100%
• multi agent 75%
• Decision-Making 25%
• State Space 25%
• Dynamic Environment 25%
• System Management 25%
• Function Value 25%
• Complex Function 25%
• Solution Procedure 25%
• Learning Framework 25%
• Reinforcement Learning 25%
• Operating System 25%
• High Dimensional Space 25%

Keyphrases

• Large Action Space 100%
• Multi-agent Actor-critic 100%
• Partially Observable MDP 66%
• Network Solution 33%
• Actor-critic Deep Reinforcement Learning 33%
• Deep Q-network 33%
• Deep Reinforcement Learning Algorithm 33%
• Condition-based Inspections 33%
• Factorized Representations 33%