Truncated horizon Policy Search: Combining Reinforcement Learning & Imitation Learning.
Wen SunJ. Andrew BagnellByron BootsPublished in: ICLR (Poster) (2018)
Keyphrases
- policy search
- reinforcement learning
- imitation learning
- reinforcement learning algorithms
- continuous state
- reinforcement learning methods
- function approximation
- state space
- reward function
- multi agent
- control problems
- markov decision processes
- model free
- dynamic programming
- action selection
- temporal difference
- partially observable markov decision processes
- policy iteration
- supervised learning
- function approximators
- transfer learning
- optimal policy
- learning problems
- partially observable
- markov decision process