Reward Value-Based Goal Selection for Agents' Cooperative Route Learning Without Communication in Reward and Goal Dynamism.
Fumito UwanoKeiki TakadamaPublished in: SN Comput. Sci. (2020)
Keyphrases
- autonomous agents
- multi agent systems
- reward signal
- multi agent
- cooperative
- intelligent behavior
- reinforcement learning
- dynamic environments
- rational agents
- agent behavior
- learning algorithm
- learning agent
- supervised learning
- learning process
- online learning
- agent communication
- learning capabilities
- communication protocol
- learning tasks
- inverse reinforcement learning
- active learning
- distributed problem solving
- multiagent learning
- interacting agents
- partially observable environments
- resource allocation