Internal Rewards Mitigate Agent Boundedness.
Jonathan SorgSatinder P. SinghRichard L. LewisPublished in: ICML (2010)
Keyphrases
- internal states
- multi agent systems
- multi agent
- reinforcement learning
- sufficient conditions
- internal state
- multiagent systems
- software agents
- autonomous agents
- reward function
- multiple agents
- agent systems
- decision making
- agent architecture
- dynamic environments
- intelligent agents
- agent model
- goal directed
- mobile agents
- internal and external
- conversational agent
- artificial agents
- agent oriented
- agent technology
- action selection
- markov decision process
- virtual agents
- reasoning process
- evolutionary algorithm
- expected reward
- multiarmed bandit
- multi armed bandits