Imitation-Projected Policy Gradient for Programmatic Reinforcement Learning.
Abhinav VermaHoang Minh LeYisong YueSwarat ChaudhuriPublished in: CoRR (2019)
Keyphrases
- policy gradient
- reinforcement learning
- actor critic
- reinforcement learning algorithms
- function approximation
- policy search
- model free reinforcement learning
- reinforcement learning methods
- state space
- model free
- state action
- optimal policy
- markov decision processes
- policy gradient methods
- optimal control
- function approximators
- partially observable markov decision processes
- approximate dynamic programming
- temporal difference learning
- temporal difference
- action selection
- gradient method
- learning problems
- dynamic programming
- multi agent
- machine learning
- action space
- control problems
- neural network
- rl algorithms
- kernel methods
- transfer learning
- support vector