Task Independent Capsule-Based Agents for Deep Q-Learning.
Akash SinghTom De SchepperKevin MetsPeter HellinckxJosé OramasSteven LatréPublished in: BNAIC/BENELEARN (2021)
Keyphrases
- multi agent
- cooperative
- multi agent systems
- action selection
- single agent
- multiple agents
- multiagent systems
- multiagent learning
- autonomous agents
- reinforcement learning
- intelligent agents
- multi agent reinforcement learning
- learning algorithm
- learning agent
- agent receives
- software agents
- mobile agents
- state space
- agent architecture
- optimal policy
- dynamic environments
- incomplete information
- distributed agents
- endoscopic images
- agent systems
- decision making
- artificial agents
- coalition formation
- agent technology
- resource allocation
- learning agents
- agent model
- function approximation