Safe multi-agent deep reinforcement learning for joint bidding and maintenance scheduling of generation units.
Pegah RokhforozOlga FinkPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- multi agent
- preventive maintenance
- scheduling problem
- scheduling algorithm
- state space
- multi agent environments
- cooperative
- dynamic programming
- multi agent systems
- model free
- software maintenance
- single agent
- markov decision processes
- function approximation
- machine learning
- reinforcement learning algorithms
- learning agents
- multiagent systems
- optimal policy
- learning process
- round robin
- generation process
- learning algorithm
- combinatorial auctions
- online auctions
- temporal difference
- cognitive agents
- single machine
- autonomous agents
- multi agent reinforcement learning
- heterogeneous agents
- multi issue
- intelligent agents
- multiagent reinforcement learning
- reinforcement learning agents