Model-Free Imitation Learning with Policy Optimization.
Jonathan HoJayesh K. GuptaStefano ErmonPublished in: ICML (2016)
Keyphrases
- model free
- imitation learning
- reinforcement learning
- policy iteration
- reinforcement learning methods
- policy evaluation
- reinforcement learning algorithms
- average reward
- optimal policy
- temporal difference
- function approximation
- action selection
- maximum margin
- reward function
- partially observable markov decision processes
- markov decision process
- state space
- infinite horizon
- robotic systems
- transfer learning
- control system