Adversarially Regularized Policy Learning Guided by Trajectory Optimization.
Zhigen ZhaoSimiao ZuoTuo ZhaoYe ZhaoPublished in: L4DC (2022)
Keyphrases
- knowledge acquisition
- learning problems
- learning algorithm
- reinforcement learning
- neural network
- inductive inference
- prior knowledge
- optimization problems
- online learning
- learning systems
- risk minimization
- action selection
- learning scenarios
- learning tasks
- mobile learning
- background knowledge
- optimization algorithm
- learning process
- spatio temporal
- training data