A Partially Observable Markov-Decision-Process-Based Blackboard Architecture for Cognitive Agents in Partially Observable Environments.
Hideaki ItohHidehiko NakanoRyota TokushimaHisao FukumotoHiroshi WakuyaPublished in: IEEE Trans. Cogn. Dev. Syst. (2022)
Keyphrases
- blackboard architecture
- cognitive agents
- partially observable environments
- knowledge sources
- inverse reinforcement learning
- knowledge based systems
- real time control
- reinforcement learning algorithms
- inference engine
- partially observable
- multi agent systems
- reinforcement learning
- mental states
- multi agent
- complex domains
- defeasible logic
- knowledge base
- cooperative games
- domain knowledge
- bdi agents
- domain specific
- temporal difference
- partially observable markov decision processes
- machine learning
- expert systems
- rough sets
- markov decision processes
- error rate
- knowledge acquisition