Offline reinforcement learning application in robotic manipulation with a COG method case.
Yanpeng HuoYuning LiangPublished in: CCEAI (2022)
Keyphrases
- reinforcement learning
- high accuracy
- detection method
- preprocessing
- clustering method
- high precision
- experimental evaluation
- synthetic data
- computationally efficient
- least squares
- state space
- significant improvement
- computational complexity
- theoretical analysis
- similarity measure
- fitted q iteration
- segmentation algorithm
- transition model
- real time
- support vector machine svm
- denoising
- support vector machine
- mobile robot
- dynamic programming
- bayesian networks
- genetic algorithm