Image-based Regularization for Action Smoothness in Autonomous Miniature Racing Car with Deep Reinforcement Learning.
Hoang-Giang CaoI LeeBo-Jiun HsuZheng-Yi LeeYu-Wei ShihHsueh-Cheng WangI-Chen WuPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- smoothing parameter
- autonomous learning
- car racing
- action selection
- partially observable domains
- action space
- prior information
- function approximation
- state action
- cooperative
- reward shaping
- temporal difference
- cost function
- markov decision processes
- machine learning
- reinforcement learning algorithms
- learning process
- learning capabilities
- agent learns
- fitted q iteration
- model free
- learning problems
- optimal policy
- computer vision
- learning algorithm
- regularization parameter
- robotic systems
- deep learning
- autonomous navigation
- transfer learning
- regularization method
- supervised learning
- state space
- dynamic programming
- smoothness term
- neural network