Optimizing Agent Training with Deep Q-Learning on a Self-Driving Reinforcement Learning Environment.
Pedro RodriguesSusana M. VieiraPublished in: SSCI (2020)
Keyphrases
- learning environment
- reinforcement learning
- multi agent
- agent receives
- action selection
- pedagogical agents
- cooperative
- multi agent systems
- learning agent
- state space
- function approximation
- intelligent agents
- single agent
- state action
- multiple agents
- multiagent systems
- exploration strategy
- training process
- autonomous agents
- continuous state and action spaces
- agent model
- learning systems
- learning algorithm
- learning activities
- learning outcomes
- neural network
- deep architectures
- multi agent reinforcement learning
- multiagent learning
- e learning
- learning process
- model free
- mobile agents
- training data
- markov decision process
- dynamic environments
- decision making
- multi agent learning
- decision theoretic
- training samples
- optimal policy
- machine learning
- learning experience