Reinforcement learning based agents for improving layouts of automotive crash structures.
Jens TrillingAxel SchumacherMing ZhouPublished in: Appl. Intell. (2024)
Keyphrases
- reinforcement learning
- multi agent
- learning agents
- multi agent systems
- action selection
- multiple agents
- single agent
- multi agent environments
- reinforcement learning agents
- intelligent agents
- multiagent systems
- function approximation
- cooperative
- multi agent reinforcement learning
- software agents
- agent receives
- autonomous agents
- evolutionary learning
- partial observability
- agent behavior
- dynamic environments
- agent systems
- robocup soccer
- learning agent
- decision making
- learning capabilities
- learning process
- multiagent reinforcement learning
- learned knowledge
- markov decision processes
- complex domains
- model free
- reinforcement learning methods
- complex environments
- multiagent learning
- agent architecture
- neural network
- state space
- resource allocation
- decentralized control
- agent model
- agent interactions
- action space
- reinforcement learning algorithms
- social welfare
- markov decision process
- partially observable