Reinforcement Learning for Multi-Agent Stochastic Resource Collection.
Niklas StraußDavid WinkelMax BerrendorfMatthias SchubertPublished in: ECML/PKDD (4) (2022)
Keyphrases
- reinforcement learning
- multi agent
- direct policy search
- learning automata
- function approximation
- state space
- multi agent environments
- document collections
- control policies
- cooperative
- resource constraints
- stochastic approximation
- monte carlo
- multi agent reinforcement learning
- control problems
- intelligent agents
- multi agent systems
- stochastic model
- single agent
- markov decision processes
- model free
- database
- continuous state spaces
- web resources
- resource management
- heterogeneous agents
- partially observable
- transfer learning
- resource allocation
- optimal policy
- reinforcement learning agents
- dynamic programming
- learning agents
- learning classifier systems
- resource selection
- function approximators
- action space
- agent oriented
- reinforcement learning algorithms
- coalition formation
- autonomous agents
- multiagent systems
- supervised learning
- machine learning