Improving Generalization in Reinforcement Learning Through Forked Agents.
Olivier MoulinVincent François-LavetPaul W. G. ElbersMark HoogendoornPublished in: IEA/AIE (2) (2023)
Keyphrases
- reinforcement learning
- multi agent
- learning agents
- multi agent systems
- action selection
- multi agent environments
- intelligent agents
- multi agent reinforcement learning
- cooperative
- learning agent
- software agents
- multiple agents
- multiagent learning
- agent behavior
- agent receives
- single agent
- learning capabilities
- dynamic environments
- multiagent systems
- agent architecture
- autonomous agents
- reinforcement learning algorithms
- learning algorithm
- multiagent reinforcement learning
- temporal difference
- resource allocation
- agent technology
- robocup soccer
- reinforcement learning agents
- distributed agents
- state space
- mobile agents
- agent systems
- incomplete information
- decentralized control
- interacting agents
- decision making
- optimal control
- decision theoretic
- agent model
- agent interactions
- social welfare
- reinforcement learning methods
- partial observability
- function approximation
- model free