Heterogeneous team deep q-learning in low-dimensional multi-agent environments.
Mateusz KurekWojciech JaskowskiPublished in: CIG (2016)
Keyphrases
- multi agent environments
- low dimensional
- multi agent
- reinforcement learning
- reinforcement learning algorithms
- high dimensional
- reinforcement learning methods
- multi agent systems
- single agent
- autonomous agents
- dimensionality reduction
- state space
- cooperative
- function approximation
- feature space
- principal component analysis
- markov decision processes
- model free
- data points
- multiagent systems
- learning algorithm
- multiple agents
- optimal policy
- input space
- neural network
- decision problems
- action selection
- dynamical systems
- function approximators
- machine learning
- data mining