Context-Aware Composition of Agent Policies by Markov Decision Process Entity Embeddings and Agent Ensembles.
Nicole MerkleRalf MikutPublished in: CoRR (2023)
Keyphrases
- markov decision process
- context aware
- reward function
- optimal policy
- reinforcement learning
- state space
- contextual information
- multi agent systems
- multi agent
- context awareness
- markov decision processes
- intelligent agents
- finite horizon
- ubiquitous computing
- multiple agents
- ambient intelligence
- markov games
- infinite horizon
- current context
- software agents
- mobile agents
- mobile devices
- decision making
- multiagent systems
- agent technology
- smart home
- transition probabilities
- total cost
- learning algorithm
- policy iteration
- intelligent systems
- context aware services