MicroRacer: A Didactic Environment for Deep Reinforcement Learning.
Andrea AspertiMarco Del BruttoPublished in: LOD (1) (2022)
Keyphrases
- reinforcement learning
- real time
- learning process
- mobile robot
- virtual world
- learning algorithm
- dynamic environments
- virtual environment
- learning processes
- agent learns
- multi agent environments
- autonomous learning
- environmental conditions
- optimal control
- markov decision processes
- hidden markov models
- information systems
- machine learning
- neural network