Curriculum-Based Reinforcement Learning for Pedestrian Simulation: Towards an Explainable Training Process?
Giuseppe VizzariDaniela BriolaThomas CecconelloPublished in: WOA (2023)
Keyphrases
- training process
- reinforcement learning
- training data
- learning process
- neural network
- adaptation process
- adaboost algorithm
- support vector machine
- real robot
- simulation model
- high school
- neural network structure
- reinforcement learning algorithms
- training algorithm
- markov decision processes
- semi supervised
- function approximation
- multi agent
- machine learning
- kernel parameters
- data mining
- optimal policy
- model free
- temporal difference
- object detection