A population-based approach for multi-agent interpretable reinforcement learning.
Marco CrespiAndrea FerigoLeonardo Lucio CustodeGiovanni IaccaPublished in: Appl. Soft Comput. (2023)
Keyphrases
- reinforcement learning
- multi agent
- function approximation
- state space
- intelligent agents
- single agent
- markov decision processes
- population size
- multi agent reinforcement learning
- learning agents
- multiagent systems
- temporal difference
- model free
- multi agent systems
- reinforcement learning algorithms
- optimal policy
- agent oriented
- dynamic programming
- learning process
- cooperative
- multiagent reinforcement learning
- traffic signal control
- machine learning
- software agents
- autonomous agents
- agent communication
- state abstraction
- reinforcement learning agents
- demographic data