AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agents.
Jake GrigsbyLinxi FanYuke ZhuPublished in: ICLR (2024)
Keyphrases
- reinforcement learning
- multi agent
- learning capabilities
- multi agent systems
- learning agents
- adaptive behavior
- intelligent agents
- agent receives
- open environments
- software agents
- mobile agents
- agent systems
- contextual information
- multiagent learning
- multi agent decision making
- evolutionary learning
- multiple agents
- autonomous agents
- multiagent systems
- context aware
- state space
- cooperative
- optimal control
- function approximation
- game theory
- resource allocation
- artificial agents
- partial observability
- learning process
- interacting agents
- machine learning