Model-Free Imitation Learning with Policy Optimization.
Jonathan HoJayesh K. GuptaStefano ErmonPublished in: CoRR (2016)
Keyphrases
- model free
- imitation learning
- reinforcement learning
- policy iteration
- policy evaluation
- reinforcement learning methods
- optimal policy
- reinforcement learning algorithms
- function approximation
- average reward
- temporal difference
- markov decision processes
- action selection
- markov decision process
- humanoid robot
- partially observable markov decision processes
- state space
- function approximators
- infinite horizon
- relational data
- feature selection