Why the 'selfish' optimizing agents could solve the decentralized reinforcement learning problems.
Thanh NguyenSnehasis MukhopadhyayMeghna Babbar-SebensPublished in: AI Commun. (2019)
Keyphrases
- multi agent
- reinforcement learning problems
- cooperative
- multi agent systems
- resource allocation
- reinforcement learning algorithms
- neural network
- multiagent systems
- multiagent reinforcement learning
- markov decision problems
- multiple agents
- reinforcement learning
- decision theoretic
- function approximation
- dynamic environments
- single agent
- action space
- state space
- decision making