L2C2: Locally Lipschitz Continuous Constraint towards Stable and Smooth Reinforcement Learning.
Taisuke KobayashiPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- robotic control
- model free
- function approximation
- linear constraints
- smoothness constraint
- state space
- markov decision processes
- temporal difference
- neural network
- reinforcement learning algorithms
- robot control
- image sequences
- learning algorithm
- learning process
- machine learning
- consistency constraints
- global consistency
- constrained minimization
- real world