Safer Reinforcement Learning for Agents in Industrial Grid-Warehousing.
Per-Arne AndersenMorten GoodwinOle-Christoffer GranmoPublished in: LOD (2) (2020)
Keyphrases
- reinforcement learning
- multi agent
- multi agent systems
- learning agents
- action selection
- multi agent environments
- single agent
- learning agent
- intelligent agents
- agent receives
- multiple agents
- multiagent systems
- multi agent reinforcement learning
- software agents
- cooperative
- robocup soccer
- autonomous agents
- reinforcement learning agents
- industrial applications
- multiagent learning
- artificial agents
- coalition formation
- dynamic environments
- agent systems
- resource allocation
- learning process
- state space
- optimal policy
- data warehouse
- learning capabilities
- agent architecture
- evolutionary learning
- mobile agents
- reinforcement learning algorithms
- temporal difference
- incomplete information
- agent model
- agent technology
- decentralized control
- agent learns
- learning algorithm
- agent behavior
- grid environment
- virtual organization
- decision theoretic
- grid computing
- function approximation
- planning problems
- markov decision processes